© 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. 12-GEMMASCOPE-2-RES-16K
    4. 7774
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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_12_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
    <eos>
    1.14
     继续访问
    0.88
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.67
    </code>
    0.64
     Below
    0.63
    </h1>
    0.63
    ↵↵
    0.61
     }}$.
    0.61
    <unused60>
    0.59
    ↵↵↵↵↵↵↵↵↵↵
    0.58
    POSITIVE LOGITS
    ”、“
    2.33
    .;
    2.22
    $;
    2.18
    !;
    2.18
    ;
    2.16
     Gresham
    2.13
    ”;
    2.05
    /;
    2.04
    ;
    2.00
    ﹔
    1.98
    Activations Density 0.142%

    No Known Activations