© 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. 64820
    Prev
    Next
    INDEX
    Explanations

    build up

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

    identifying negatives

    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
     hermaph
    0.54
     Gaia
    0.50
     недвижимости
    0.49
     GaAs
    0.49
     McKin
    0.46
     élev
    0.46
    ↵
    0.44
     unisex
    0.44
     Sharon
    0.44
     asymmetrical
    0.43
    POSITIVE LOGITS
    ']*
    0.48
    érale
    0.47
    Ϳ
    0.47
    ў
    0.44
    😮
    0.44
    ὢ
    0.43
    imètres
    0.43
     Віль
    0.43
     zespo
    0.42
    Ἐ
    0.42
    Activations Density 0.000%

    No Known Activations