© 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. 33194
    Prev
    Next
    INDEX
    Explanations

    actors and people featured

    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
     after
    -1.70
     while
    -1.66
     In
    -1.66
     can
    -1.48
     D
    -1.44
     will
    -1.44
     or
    -1.43
     for
    -1.43
     if
    -1.40
     would
    -1.39
    POSITIVE LOGITS
     lác
    1.81
     unſ
    1.81
     ſever
    1.78
     ſont
    1.65
     pourront
    1.65
     cóc
    1.60
     Reſ
    1.59
    Ook
    1.56
     auront
    1.55
     kenal
    1.55
    Activations Density 0.025%

    No Known Activations