© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116760
    Prev
    Next
    INDEX
    Explanations

    tied for position or score

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags standalone numeric tokens, especially those appearing in statistical or tabular data.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    ranking positions and competitive standings in sports or contests.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of ties or equality—situations where participants are level in rank, score, or contribution (e.g., dead heats, tied standings, equal contributions).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    üns
    -0.76
    роме
    -0.74
     sowie
    -0.72
    ир
    -0.72
     además
    -0.72
    揄
    -0.71
    beginTransaction
    -0.68
     подключения
    -0.68
    emic
    -0.68
    param
    -0.67
    POSITIVE LOGITS
     tied
    3.09
     tie
    2.89
     joint
    2.86
    joint
    2.30
     shared
    2.22
     Tied
    2.22
    tied
    2.19
    Tied
    2.11
    Tie
    2.09
     TIE
    2.05
    Activations Density 0.025%

    No Known Activations