© 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. 208
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    2.12
     that
    1.99
     to
    1.97
     is
    1.96
     has
    1.93
     have
    1.87
     with
    1.87
     a
    1.84
     was
    1.81
     in
    1.80
    POSITIVE LOGITS
     cosidd
    1.64
     例えば
    1.56
    퍁
    1.56
    𒌷
    1.55
    𒆳
    1.54
    𒉈
    1.54
    𒀊
    1.50
    𒅆
    1.50
     moż
    1.49
     âmbito
    1.49
    Activations Density 1.413%

    No Known Activations