© 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. 25650
    Prev
    Next
    INDEX
    Explanations

    additional insured

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

    explaining concepts

    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
     значи
    0.48
     цвета
    0.46
    ры
    0.45
     срав
    0.45
     ziren
    0.45
     თ
    0.45
     используется
    0.45
     było
    0.44
     подой
    0.44
    寵
    0.44
    POSITIVE LOGITS
    hood
    0.52
    Outgoing
    0.49
    atlan
    0.48
    액
    0.47
     Ath
    0.46
    شارة
    0.45
    doFilter
    0.45
    axes
    0.44
    ality
    0.44
     advertis
    0.43
    Activations Density 0.000%

    No Known Activations