© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10162
    Prev
    Next
    INDEX
    Explanations

    the Trevor Project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Swamp
    1.04
     डेंगू
    1.01
     marais
    1.00
     marshes
    0.99
     orchard
    0.95
     swamps
    0.94
    フィールド
    0.92
    沭
    0.92
     campo
    0.90
     orchards
    0.90
    POSITIVE LOGITS
    先端
    0.96
    tip
    0.90
     edges
    0.85
     edge
    0.85
     Reputation
    0.84
     coast
    0.83
    fragments
    0.83
     diamante
    0.82
     Kenyan
    0.81
    coast
    0.80
    Activations Density 0.104%

    No Known Activations