© 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. 65557
    Prev
    Next
    INDEX
    Explanations

    decisions and responsibilities

    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
     PARTS
    -1.09
    dorfer
    -1.02
     где
    -1.02
     Pistons
    -0.98
     LOAN
    -0.97
     DOLLARS
    -0.96
     sáb
    -0.96
     هذا
    -0.95
    opie
    -0.95
     Peut
    -0.95
    POSITIVE LOGITS
     by
    1.40
     individual
    1.28
     entirely
    1.23
     solely
    1.23
     individuals
    1.21
     people
    1.16
     our
    1.16
     profoundly
    1.11
     your
    1.11
     sepenuhnya
    1.10
    Activations Density 0.029%

    No Known Activations