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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110519
    Prev
    Next
    INDEX
    Explanations

    input related terms

    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
    酿
    -0.84
    껏
    -0.83
    orithmic
    -0.81
     soát
    -0.79
     poulet
    -0.77
     tama
    -0.77
    (ﾟ
    -0.76
     carnet
    -0.76
    叶修
    -0.75
    )।
    -0.75
    POSITIVE LOGITS
     quella
    0.83
     again
    0.80
     melden
    0.77
    syst
    0.76
    DllImport
    0.75
    હ
    0.75
     Poseidon
    0.74
    zp
    0.74
     rendszer
    0.73
     paznok
    0.72
    Activations Density 0.008%

    No Known Activations