© 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. 99139
    Prev
    Next
    INDEX
    Explanations

    BBP standard

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

    Retro film and media

    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
     addCriterion
    0.51
    𒂠
    0.49
    ères
    0.49
    dą
    0.48
     ပြ
    0.48
    ändig
    0.47
     सत्यापित
    0.47
    šnje
    0.47
    ⊢
    0.47
     coef
    0.47
    POSITIVE LOGITS
     Bradbury
    0.48
    UFF
    0.48
    R
    0.47
     Barkley
    0.46
     R
    0.45
     B
    0.45
    Te
    0.45
     Retro
    0.45
    Retro
    0.44
     Film
    0.44
    Activations Density 0.000%

    No Known Activations