© 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. 93494
    Prev
    Next
    INDEX
    Explanations

    code comments or structure

    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
     hooked
    -0.84
     found
    -0.84
    dată
    -0.83
     desbloquear
    -0.80
     заключается
    -0.80
    某种
    -0.80
    锻炼
    -0.79
     appelez
    -0.79
    unzione
    -0.78
    espèce
    -0.77
    POSITIVE LOGITS
    </b>
    0.91
    </h2>
    0.90
    );
    
    0.84
     (_)
    0.82
    JNI
    0.79
    ╚
    0.79
    ());
    0.78
     összefoglal
    0.77
    的他
    0.77
    mathbb
    0.75
    Activations Density 0.001%

    No Known Activations