© 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. 109773
    Prev
    Next
    INDEX
    Explanations

    wikipedia and wikimedia content

    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
    椰
    -0.75
    OAK
    -0.75
     ане
    -0.75
     electrified
    -0.75
    īb
    -0.75
    Huge
    -0.75
    метров
    -0.74
     DHA
    -0.73
    常
    -0.73
     Napier
    -0.73
    POSITIVE LOGITS
     skin
    1.05
     MW
    0.95
    skin
    0.95
    Mw
    0.94
    wg
    0.93
    wikimedia
    0.88
     Wikimedia
    0.88
     mw
    0.85
     parser
    0.84
    mw
    0.83
    Activations Density 0.030%

    No Known Activations