© 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. 34-GEMMASCOPE-RES-131K
    7. 78636
    Prev
    Next
    INDEX
    Explanations

    javascript module imports

    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_34/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
    雜
    -1.02
     Trag
    -0.87
    _",
    -0.85
    頗
    -0.83
    ?}",
    -0.82
    讚
    -0.82
     佐
    -0.80
     parma
    -0.80
    ɹ
    -0.79
    マーケット
    -0.78
    POSITIVE LOGITS
    ";
    1.51
    ”;
    1.30
    ’;
    1.17
    ];
    1.12
    ');
    1.11
    ';
    1.10
    ();
    1.09
    槻
    1.01
    ticelli
    1.00
    ");
    0.99
    Activations Density 0.026%

    No Known Activations