© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66836
    Prev
    Next
    INDEX
    Explanations

    code snippets or file paths

    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
     Selama
    -1.03
    iamo
    -1.02
    ième
    -1.00
    ਗ਼
    -0.98
     APPELLANT
    -0.97
     Diseño
    -0.96
     Però
    -0.95
     geralmente
    -0.95
     التالية
    -0.93
     تهران
    -0.93
    POSITIVE LOGITS
     and
    1.79
     of
    1.24
     but
    1.16
     a
    1.10
     or
    1.06
     terminology
    1.00
     from
    1.00
     will
    0.98
     to
    0.98
     way
    0.97
    Activations Density 0.000%

    No Known Activations