© 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. 27735
    Prev
    Next
    INDEX
    Explanations

    loop counter initialization

    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
    几分
    -1.14
    haviours
    -0.98
    Sheriff
    -0.90
     meisje
    -0.88
    before
    -0.87
    loài
    -0.87
     spørsmål
    -0.86
     tertentu
    -0.85
    riel
    -0.85
    resave
    -0.84
    POSITIVE LOGITS
    ógy
    0.89
     piernas
    0.89
    苓
    0.86
    agaan
    0.85
    vestidos
    0.85
     муніципалі
    0.85
    getreten
    0.84
    letor
    0.84
    Katso
    0.84
     anglès
    0.82
    Activations Density 0.019%

    No Known Activations