© 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. 92584
    Prev
    Next
    INDEX
    Explanations

    Q: questions

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

    The neuron responds primarily to numeric tokens—i.e. numbers or number‐like strings.

    oai_token-act-pair · o4-miniTriggered 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
    ผล
    -0.90
     frango
    -0.88
     steder
    -0.82
    žių
    -0.82
     Kemal
    -0.80
    unoz
    -0.79
    Ў
    -0.78
     Indexing
    -0.78
     forfait
    -0.76
     Merger
    -0.76
    POSITIVE LOGITS
    NotExist
    0.86
     دارای
    0.82
    tiene
    0.81
     verfolgen
    0.79
    ofu
    0.79
     behe
    0.78
    Trop
    0.77
    María
    0.76
    MessageInfo
    0.75
    PERTIES
    0.75
    Activations Density 0.000%

    No Known Activations