© 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. 15902
    Prev
    Next
    INDEX
    Explanations

    but

    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
    駅から
    -1.04
     may
    -0.99
     or
    -0.98
    Bruh
    -0.97
    Idk
    -0.95
     could
    -0.93
     from
    -0.91
     вероятно
    -0.90
    这也
    -0.90
    KELEY
    -0.89
    POSITIVE LOGITS
     but
    5.19
     nhưng
    3.48
     แต่
    2.98
     αλλά
    2.91
     BUT
    2.89
     tetapi
    2.89
     namun
    2.83
     yet
    2.72
     लेकिन
    2.72
     pero
    2.69
    Activations Density 0.080%

    No Known Activations