© 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. 322
    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
     defaultstate
    2.37
    酭
    2.32
    ্ড
    2.24
    কে
    2.22
    agic
    2.22
     CASCADE
    2.13
     SUBSTIT
    2.10
     PROCEDURE
    2.10
     シル
    2.09
    க்ஸாண்ட
    2.08
    POSITIVE LOGITS
    pubmed
    1.76
    3
    1.76
    wt
    1.75
    Os
    1.75
    ਏ
    1.74
    \%,
    1.73
    \%.
    1.71
    Gt
    1.71
    spl
    1.69
    FT
    1.68
    Activations Density 1.258%

    No Known Activations