© 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. 14844
    Prev
    Next
    INDEX
    Explanations

    concern and discussion

    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
     You
    -2.05
     начинают
    -1.87
    剛
    -1.84
    Skocz
    -1.83
     Añade
    -1.82
     accompagner
    -1.81
    ⅰ
    -1.78
     Você
    -1.77
     Agrega
    -1.74
     erlä
    -1.73
    POSITIVE LOGITS
    ↵↵
    2.58
    赑
    2.14
    \
    1.92
    </em>
    1.90
    蔟
    1.83
    lessly
    1.79
     or
    1.79
    or
    1.77
     about
    1.73
     suiker
    1.69
    Activations Density 0.026%

    No Known Activations