© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130521
    Prev
    Next
    INDEX
    Explanations

    names followed by initials or titles

    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
     stolet
    -1.29
    providedIn
    -1.23
     Senhor
    -1.10
     Drž
    -1.06
    にならない
    -1.03
    ごちそう
    -1.00
     Acesso
    -0.98
     Melhor
    -0.97
     матері
    -0.97
     to
    -0.97
    POSITIVE LOGITS
    当然
    1.01
     cœurs
    0.93
    甚至
    0.90
    思議
    0.90
     pár
    0.90
     ..."
    0.90
     escolha
    0.89
    гона
    0.89
     sahiptir
    0.88
     Größe
    0.88
    Activations Density 0.014%

    No Known Activations