© 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. 86521
    Prev
    Next
    INDEX
    Explanations

    anesthesia profession

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

    banana

    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
     zás
    0.49
     아름
    0.47
     IDENTITY
    0.46
    峀
    0.46
     활용
    0.45
    ками
    0.44
    垐
    0.43
    ⿲
    0.42
     Messrs
    0.42
     GPI
    0.42
    POSITIVE LOGITS
     Tính
    0.48
    Producer
    0.47
     Tok
    0.46
    Popup
    0.45
     Rae
    0.45
    fence
    0.45
    焼け
    0.45
    Pren
    0.44
    ologic
    0.44
    Disclosure
    0.43
    Activations Density 0.000%

    No Known Activations