© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83253
    Prev
    Next
    INDEX
    Explanations

    comedies and filmographies

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

    This neuron fires on dialogue‐style speaker labels and associated punctuation (e.g. character names followed by colons and parenthetical stage directions).

    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
    ABULARY
    -0.76
    一分
    -0.76
     își
    -0.74
    姊
    -0.74
    plash
    -0.73
    Así
    -0.73
    jazz
    -0.70
     tumbling
    -0.70
    媛
    -0.70
     jazz
    -0.69
    POSITIVE LOGITS
     comedies
    0.98
     entourage
    0.84
     Nitro
    0.84
     Hva
    0.81
    lamydia
    0.81
     Clerks
    0.81
    userModel
    0.80
     Pyro
    0.79
    Krie
    0.76
    Kings
    0.75
    Activations Density 0.034%

    No Known Activations