© 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. 22-GEMMASCOPE-RES-131K
    7. 36651
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by specific words

    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
    yscale
    -1.00
    :
    -0.99
    u
    -0.96
     ど
    -0.94
     Ministero
    -0.93
    !
    -0.91
    game
    -0.89
    ｉ
    -0.89
    ouk
    -0.89
     ensure
    -0.88
    POSITIVE LOGITS
     trám
    1.17
     炖
    1.16
    ierten
    1.12
     bát
    1.09
    saucony
    1.08
    gunaan
    1.02
    ilarang
    0.98
    вели
    0.98
    contain
    0.97
     bolsos
    0.96
    Activations Density 0.067%

    No Known Activations