© 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. 128875
    Prev
    Next
    INDEX
    Explanations

    past punctuation

    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
     from
    -1.80
     their
    -1.63
     recetas
    -1.56
     any
    -1.55
     which
    -1.53
     tersenyum
    -1.52
    nosotros
    -1.52
    område
    -1.52
     at
    -1.51
     that
    -1.50
    POSITIVE LOGITS
     was
    1.95
     also
    1.86
     didn
    1.82
     have
    1.79
     has
    1.77
     is
    1.76
    '
    1.75
     already
    1.64
     said
    1.61
     know
    1.58
    Activations Density 0.039%

    No Known Activations