© 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. 128831
    Prev
    Next
    INDEX
    Explanations

    cases (eyes, hips, patients)

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers in parentheses followed by units (like eyes, patients, or percentages).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     visites
    -1.27
     ucap
    -1.16
     appartement
    -1.15
    𖧵
    -1.15
    utilized
    -1.12
     Feinde
    -1.11
    
    -1.09
    ſi
    -1.07
    generally
    -1.07
     fruta
    -1.04
    POSITIVE LOGITS
     ambiguities
    1.24
     of
    0.97
     resurrect
    0.95
    었
    0.92
     województ
    0.90
     revital
    0.89
    はな
    0.88
     created
    0.88
     يوجد
    0.86
    erialized
    0.84
    Activations Density 0.001%

    No Known Activations