© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71455
    Prev
    Next
    INDEX
    Explanations

    stop followed by other words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    -3.13
    蚨
    -2.78
     
    -2.42
     tomando
    -2.41
     –
    -2.34
     所以
    -2.33
    THE
    -2.31
     而
    -2.28
    牆
    -2.28
    走进
    -2.19
    POSITIVE LOGITS
    ꜆
    2.91
    );
    2.80
    ();
    2.70
     utilisée
    2.64
    檍
    2.63
    嗵
    2.58
    ”;
    2.56
    ()));
    2.52
     ).
    2.52
    ];
    2.52
    Activations Density 0.014%

    No Known Activations