© 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. 106788
    Prev
    Next
    INDEX
    Explanations

    drinking cup or glass

    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
    XV
    -0.76
     Kemp
    -0.74
    Aggregate
    -0.73
    outons
    -0.73
     بست
    -0.73
     çı
    -0.71
     oven
    -0.71
     bb
    -0.71
    ประกอบ
    -0.70
     करेंगे
    -0.70
    POSITIVE LOGITS
     cup
    1.11
    杯
    1.05
    盃
    1.05
     cups
    1.00
     poured
    0.97
     wine
    0.90
    撮影
    0.83
     emptied
    0.83
     filled
    0.82
    酹
    0.82
    Activations Density 0.012%

    No Known Activations