© 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. 106610
    Prev
    Next
    INDEX
    Explanations

    and following conjunctions

    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
     både
    -1.80
     and
    -1.71
     trám
    -1.66
     zarówno
    -1.63
     нашего
    -1.63
    ෆ
    -1.62
     rése
    -1.59
     kabát
    -1.54
     botines
    -1.49
     lã
    -1.47
    POSITIVE LOGITS
     at
    2.16
     even
    2.11
     without
    1.95
     consequently
    1.95
     by
    1.94
     especially
    1.94
     if
    1.85
     in
    1.83
     other
    1.81
     from
    1.76
    Activations Density 0.022%

    No Known Activations