© 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. 132273
    Prev
    Next
    INDEX
    Explanations

    AI, uploads, Asw, Ass, Ais, Pip

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

    gender identity, growth, reduction

    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
    urricular
    0.46
    events
    0.45
    Events
    0.45
    animals
    0.45
    atted
    0.43
    EVENTS
    0.43
    Famil
    0.43
    ক
    0.41
    famil
    0.41
    ueill
    0.41
    POSITIVE LOGITS
     AI
    0.50
     uploads
    0.49
     Asw
    0.49
     Ass
    0.46
     Ais
    0.46
     Pip
    0.45
    weisen
    0.45
     PPAR
    0.45
    涵
    0.45
     ครับ
    0.44
    Activations Density 0.000%

    No Known Activations