© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4770
    Prev
    Next
    INDEX
    Explanations

    neuro, electro, hydro, geo prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    就不会
    0.37
     AutoML
    0.36
     Saltar
    0.34
    就没有
    0.32
    妫
    0.31
     Перейти
    0.31
     মুক্তিফৌজ
    0.31
    恿
    0.31
    禳
    0.31
    Benzoimidazol
    0.31
    POSITIVE LOGITS
    TO
    0.36
    -
    0.36
    centric
    0.36
     lysates
    0.35
    }
    0.35
    TC
    0.33
    ?
    0.31
    NE
    0.31
     enthusiasts
    0.31
     theses
    0.31
    Activations Density 0.087%

    No Known Activations