© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38699
    Prev
    Next
    INDEX
    Explanations

    section marker "2."

    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
    providedIn
    -1.23
     koncentr
    -1.16
     harus
    -1.14
    γει
    -1.13
    jaket
    -1.11
     Drž
    -1.10
     Irán
    -1.09
     internetu
    -1.08
     évé
    -1.07
    nelles
    -1.06
    POSITIVE LOGITS
     is
    1.64
    是一
    1.07
    ~
    1.05
    がお
    1.02
     что
    0.98
    athy
    0.98
     &
    0.98
    ING
    0.96
     xào
    0.95
    k
    0.95
    Activations Density 0.001%

    No Known Activations