© 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. 72229
    Prev
    Next
    INDEX
    Explanations

    you can or if you

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

    healthy masculinity

    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
     During
    0.48
     નવા
    0.47
     μέρος
    0.45
    ळी
    0.44
    憔
    0.43
     சத்திய
    0.41
    甲烷
    0.41
     месяц
    0.40
    During
    0.40
    બી
    0.40
    POSITIVE LOGITS
     或
    0.54
     implement
    0.46
    及
    0.46
    或
    0.46
     enforce
    0.45
     complete
    0.44
     则
    0.44
    strict
    0.44
     aru
    0.43
     explicación
    0.43
    Activations Density 0.002%

    No Known Activations