© 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. 64919
    Prev
    Next
    INDEX
    Explanations

    kind ofsensitive toCol. kind ofsensitive toCol

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

    clear, modern, specific, expert, data, load, dawn, Acceleration

    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
    RationalValue
    0.58
    卟
    0.52
    trashButton
    0.51
    詳細は
    0.50
    boundingBox
    0.50
    ঽ
    0.50
     സ്ത്ര
    0.50
    柔
    0.49
    宿泊
    0.49
    分组
    0.49
    POSITIVE LOGITS
    ok
    0.53
    село
    0.48
    mean
    0.46
     Playhouse
    0.46
     community
    0.45
    hi
    0.45
    она
    0.44
     Community
    0.44
    рни
    0.43
    θε
    0.42
    Activations Density 0.000%

    No Known Activations