© 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. 236718
    Prev
    Next
    INDEX
    Explanations

    harm, contact, cell, their, CD, down

    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
    OP
    0.45
    慕
    0.44
    饰
    0.44
    装饰
    0.43
     salon
    0.43
     οικο
    0.43
    泸
    0.42
    이사
    0.42
     Committed
    0.41
    的环境
    0.40
    POSITIVE LOGITS
     perceber
    0.49
    ුව
    0.46
    زاز
    0.46
    ів
    0.46
     Godfrey
    0.46
    žete
    0.46
    Vincent
    0.46
    Kb
    0.45
    ໂດຍ
    0.45
    ración
    0.45
    Activations Density 0.001%

    No Known Activations