© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204133
    Prev
    Next
    INDEX
    Explanations

    water, health, or code assumptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Entities
    0.50
    ponential
    0.46
    Conformance
    0.46
    资产
    0.44
    ها
    0.44
    渽
    0.43
    getElement
    0.43
    CategoryID
    0.43
    গ্রাম
    0.42
    प्शन
    0.42
    POSITIVE LOGITS
     Fuller
    0.47
     Dunne
    0.44
    はり
    0.41
    縷
    0.41
    full
    0.40
    fulness
    0.39
    bath
    0.38
    細菌
    0.38
     stalwart
    0.37
    getFull
    0.37
    Activations Density 0.005%

    No Known Activations