© 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. 303
    Prev
    Next
    INDEX
    Explanations

    accepted standard

    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
     entrambi
    -0.93
    cześ
    -0.93
    哚
    -0.92
    batasan
    -0.92
     nadru
    -0.90
     Statements
    -0.90
    ֪
    -0.88
    𝑂
    -0.88
     izany
    -0.88
    část
    -0.88
    POSITIVE LOGITS
     Of
    1.08
     Its
    1.00
     Reihenfolge
    0.90
     Konkurrenz
    0.88
     couvert
    0.86
    nez
    0.84
    Its
    0.83
     Mehrheit
    0.83
    くれます
    0.82
    みたら
    0.82
    Activations Density 0.137%

    No Known Activations