© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 1838
    Prev
    Next
    INDEX
    Explanations

    code elements and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    ...");
    1.87
    :");
    1.85
    .");
    1.77
    }$;
    1.75
    ..");
    1.74
     fibr
    1.73
     :");
    1.70
    .},
    1.65
     ");
    1.62
    .);
    1.62
    POSITIVE LOGITS
    ↵↵
    1.52
    ↵↵↵
    1.41
    ↵↵↵↵
    1.32
    ↵↵↵↵↵↵↵↵
    1.18
    ↵↵↵↵↵↵↵
    1.13
    ↵↵↵↵↵
    1.13
    __()
    1.12
    做什么
    1.11
    ()
    1.11
    ↵
    1.07
    Activations Density 0.026%

    No Known Activations