© 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. 64606
    Prev
    Next
    INDEX
    Explanations

    drop by spoonfuls or tablespoons

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

    hurtful or cruel jokes

    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
    相対
    0.44
     during
    0.42
    咅
    0.41
    教会
    0.41
    において
    0.41
    ゐ
    0.41
     prediction
    0.40
    同時に
    0.40
    冬
    0.40
     CHURCH
    0.40
    POSITIVE LOGITS
     الفار
    0.51
    í
    0.50
    vě
    0.49
     sú
    0.48
     lựa
    0.47
    ilà
    0.47
    gó
    0.46
    erven
    0.45
    reqParam
    0.45
    serv
    0.45
    Activations Density 0.000%

    No Known Activations