© 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. 35734
    Prev
    Next
    INDEX
    Explanations

    hexadecimal identifiers

    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
     would
    -1.57
     amigas
    -1.38
    -¡
    -1.32
    ٶ
    -1.31
     versos
    -1.29
     yıl
    -1.29
     стоковые
    -1.29
    🥊
    -1.29
    calça
    -1.28
     at
    -1.27
    POSITIVE LOGITS
    C
    1.70
    D
    1.55
    c
    1.49
    T
    1.48
    H
    1.48
    o
    1.46
    8
    1.45
     myriad
    1.43
    d
    1.41
    G
    1.41
    Activations Density 0.020%

    No Known Activations