Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110318
    Prev
    Next
    INDEX
    Explanations

    Sher, beck, Birch, Birds, Birger

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    StateMachine
    -0.78
    {`
    -0.75
    Tied
    -0.73
     poor
    -0.70
     Futter
    -0.68
    Scrollbar
    -0.68
     whome
    -0.68
    retur
    -0.68
     nearly
    -0.67
     ['$
    -0.67
    POSITIVE LOGITS
    тек
    0.81
    possibly
    0.81
    fontsize
    0.77
    probably
    0.75
    疱
    0.73
    excluding
    0.71
    onas
    0.71
    olata
    0.70
    ontes
    0.70
     excludes
    0.69
    Activations Density 0.016%

    No Known Activations