© 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. 17-GEMMASCOPE-2-RES-16K
    7. 218
    Prev
    Next
    INDEX
    Explanations

    asking for more detail?

    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_17_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
     totiž
    1.32
     infatti
    1.16
    ...@
    1.04
    様専用
    0.96
    ”（
    0.94
     म्हणजेच
    0.93
    ']],
    0.93
    ​.
    0.92
     nämlich
    0.91
    也就是
    0.91
    POSITIVE LOGITS
    ?;
    4.80
    ?
    3.87
    ?";
    3.76
    ؟
    3.69
    ;
    3.56
    ？
    3.32
    ?");
    3.27
    )?
    3.25
    );
    3.16
    ??
    2.96
    Activations Density 3.525%

    No Known Activations