© 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. 22-GEMMASCOPE-RES-131K
    7. 11384
    Prev
    Next
    INDEX
    Explanations

    anchor, Itanium, winter, fellowship

    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_22/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
     florales
    -0.91
     varier
    -0.88
     perioden
    -0.84
    "",
    -0.83
     brille
    -0.82
     brachten
    -0.82
     THEIR
    -0.82
     tyd
    -0.82
    annual
    -0.81
    position
    -0.80
    POSITIVE LOGITS
    inscrire
    0.99
     ライン
    0.92
     側
    0.86
     資料
    0.84
    odine
    0.82
     podjet
    0.82
     inspiration
    0.81
     *
    0.81
     Decline
    0.80
    тную
    0.80
    Activations Density 0.055%

    No Known Activations