© 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. 128943
    Prev
    Next
    INDEX
    Explanations

    mathematical notation variables

    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
     afore
    -1.10
     of
    -0.98
     mediocre
    -0.97
    then
    -0.93
     feuer
    -0.91
     reigning
    -0.91
     dando
    -0.90
    0
    -0.90
     vigencia
    -0.88
     Embaj
    -0.88
    POSITIVE LOGITS
     with
    1.25
    넋
    1.17
    Nazionale
    1.16
     Providing
    1.16
    Dettagli
    1.15
    Codice
    1.13
    ✕
    1.13
    باح
    1.11
    꿩
    1.10
     one
    1.09
    Activations Density 0.017%

    No Known Activations