© 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. 91226
    Prev
    Next
    INDEX
    Explanations

    harmful or illegal activities

    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
    extend
    0.48
    『
    0.47
     consigli
    0.45
    beding
    0.44
    cious
    0.43
    chtigen
    0.43
    smiling
    0.42
    proficiency
    0.42
    deriv
    0.42
     extending
    0.41
    POSITIVE LOGITS
    اً
    0.50
    σή
    0.47
    on
    0.46
    फो
    0.46
    лове
    0.41
    ंक
    0.41
    <unused1>
    0.41
     CALIFORNIA
    0.41
    宁
    0.40
     हाता
    0.40
    Activations Density 0.010%

    No Known Activations