© 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. 117341
    Prev
    Next
    INDEX
    Explanations

    black and white

    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
     зелен
    -0.84
     foglie
    -0.82
     Lippen
    -0.74
    🟩
    -0.70
     slander
    -0.70
    🐡
    -0.69
    assination
    -0.68
     beurre
    -0.68
    唉
    -0.68
    ناء
    -0.66
    POSITIVE LOGITS
     black
    2.61
     white
    2.48
    white
    2.17
    black
    2.14
     White
    2.06
     Black
    2.05
    BLACK
    1.99
     WHITE
    1.97
    Black
    1.97
     BLACK
    1.95
    Activations Density 0.013%

    No Known Activations