© 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. 7-GEMMASCOPE-2-RES-16K
    7. 216
    Prev
    Next
    INDEX
    Explanations

    specific required text

    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
     and
    3.70
     is
    3.45
     has
    3.38
     have
    3.30
    ,
    3.30
    .
    3.29
     was
    3.22
     to
    3.21
     in
    3.07
     with
    2.94
    POSITIVE LOGITS
    𒅆
    2.83
    𒉈
    2.71
    𒇽
    2.71
    𒈥
    2.70
    𒍝
    2.69
    𒀕
    2.69
     मानबी
    2.68
    𒈬
    2.68
    𒀊
    2.67
    𒀖
    2.67
    Activations Density 3.085%

    No Known Activations