© 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. 150338
    Prev
    Next
    INDEX
    Explanations

    date, manner, hero, detention

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

    biological and sexual reproduction

    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
    روح
    0.46
     propagator
    0.46
    원이
    0.45
    罨
    0.44
    ໃນ
    0.44
    埚
    0.43
    璧
    0.43
    🛎
    0.43
    ころ
    0.42
     perturb
    0.42
    POSITIVE LOGITS
    posts
    0.44
    ad
    0.44
    Estr
    0.43
     немец
    0.43
     கலைஞ
    0.42
     посте
    0.42
     गौतम
    0.42
    ofe
    0.42
    listar
    0.41
     estándares
    0.41
    Activations Density 0.003%

    No Known Activations