© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 62951
    Prev
    Next
    INDEX
    Explanations

    function arguments

    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
    ();
    -1.23
     as
    -1.11
    ];
    -1.09
    ();
    
    -1.08
     with
    -0.98
    >();
    -0.96
    ()];
    -0.93
    (),
    
    -0.91
     for
    -0.91
    (),
    -0.90
    POSITIVE LOGITS
    )
    1.24
     varandra
    0.99
    熜
    0.98
    "){
    0.95
    杩
    0.93
    ซึ่ง
    0.92
     funktioner
    0.92
    𝙪
    0.92
    conomie
    0.91
     följande
    0.91
    Activations Density 0.015%

    No Known Activations