© 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. 130997
    Prev
    Next
    INDEX
    Explanations

    agreement, past action, and invitation

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

    equations and math, context, metaphors

    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
    以來
    0.45
     increí
    0.43
    ሪያ
    0.42
    鏤
    0.41
     এদেশে
    0.39
    的可能性
    0.39
    閥
    0.39
     بف
    0.39
     complication
    0.38
    BoardManager
    0.38
    POSITIVE LOGITS
    ).
    0.44
     psychosocial
    0.43
     Context
    0.42
    att
    0.41
    थित
    0.41
     Dimensions
    0.41
     Explor
    0.41
    ams
    0.41
     Motiv
    0.41
     Enables
    0.41
    Activations Density 0.000%

    No Known Activations