© 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. 34793
    Prev
    Next
    INDEX
    Explanations

    legal and technical descriptions

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

    The neuron fires on numeric tokens, especially multi-digit numbers (e.g. years, numeric constants) in code or comments.

    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
     Crusaders
    -0.77
    omány
    -0.75
    ámara
    -0.75
    öns
    -0.73
     lemn
    -0.72
    licaciones
    -0.71
    Ли
    -0.71
    Gly
    -0.70
    網友
    -0.70
     weakens
    -0.69
    POSITIVE LOGITS
     surfaces
    0.87
     després
    0.84
     Bé
    0.82
     substrates
    0.81
     Wait
    0.77
    talking
    0.76
    yao
    0.76
     commencer
    0.74
    是真的
    0.74
    reward
    0.73
    Activations Density 0.021%

    No Known Activations