© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 177
    Prev
    Next
    INDEX
    Explanations

    resource representation

    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_7_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
    enment
    0.85
    people
    0.72
    В
    0.69
    maker
    0.68
    aree
    0.65
    PRF
    0.65
    ruled
    0.64
     ref
    0.63
     proposed
    0.62
    ‪
    0.62
    POSITIVE LOGITS
     Información
    1.05
    곍
    1.04
    ・・・。
    0.98
    ।]
    0.97
    /////////
    0.97
    뷌
    0.96
     액세
    0.95
    તાઓ
    0.94
    뿯
    0.93
     atmósfera
    0.92
    Activations Density 1.219%

    No Known Activations