© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119922
    Prev
    Next
    INDEX
    Explanations

    limited knowledge

    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_10/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
     It
    -1.80
     できる
    -1.63
     mág
    -1.59
     したい
    -1.59
    久しぶりの
    -1.58
     religiosas
    -1.57
     sesiones
    -1.55
    That
    -1.55
     producen
    -1.53
    新しい
    -1.50
    POSITIVE LOGITS
     in
    2.05
     sebag
    1.84
     of
    1.70
     sebagainya
    1.68
     also
    1.67
    н
    1.63
    n
    1.63
    AN
    1.55
     tetapi
    1.55
     for
    1.51
    Activations Density 0.013%

    No Known Activations