© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25549
    Prev
    Next
    INDEX
    Explanations

    fifty or five

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

    five and fifty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     शही
    0.45
    repl
    0.43
    ுடைய
    0.43
    parsedBlock
    0.43
    膑
    0.42
    を作成
    0.42
     २
    0.41
     লীগের
    0.41
    ⁹
    0.41
    糇
    0.41
    POSITIVE LOGITS
     cinqu
    0.50
     fifty
    0.49
     fifth
    0.48
     cinque
    0.48
     cinq
    0.47
    ’
    0.47
    Fifty
    0.47
     پانچ
    0.47
     dihar
    0.45
     cinco
    0.45
    Activations Density 0.132%

    No Known Activations