© 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. 22-GEMMASCOPE-RES-131K
    7. 65633
    Prev
    Next
    INDEX
    Explanations

    colorWith pattern or hue

    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_22/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
    lossians
    -2.80
    もちろん
    -2.36
    </h1>
    -1.92
    which
    -1.89
    1
    -1.85
     poder
    -1.80
    most
    -1.79
    は
    -1.77
    hlander
    -1.77
    us
    -1.74
    POSITIVE LOGITS
     thể
    2.11
    zelfde
    2.09
    鞮
    2.03
     valentín
    2.00
    龗
    1.96
    lmao
    1.95
     alrededores
    1.89
     ก็
    1.88
     alho
    1.87
    </em>
    1.86
    Activations Density 0.000%

    No Known Activations