© 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. 29689
    Prev
    Next
    INDEX
    Explanations

    following directions

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

    child-related 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
     bestselling
    0.44
     should
    0.44
     splendid
    0.43
     Analysis
    0.42
     differs
    0.41
     of
    0.39
    /
    0.39
    /,
    0.39
     wording
    0.38
     researched
    0.38
    POSITIVE LOGITS
     dziecko
    0.52
    溺
    0.49
     çocuğ
    0.45
     মানুষকে
    0.44
     লাফ
    0.43
    タグ
    0.43
    轎
    0.43
    եռ
    0.42
     dítě
    0.42
    ק
    0.42
    Activations Density 0.000%

    No Known Activations