© 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. 16-GEMMASCOPE-2-RES-262K
    7. 89640
    Prev
    Next
    INDEX
    Explanations

    Knives Out(" or "Actions("

    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_16_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
    ni
    0.67
     pas
    0.60
    ↵
    0.59
    ud
    0.57
    nu
    0.54
    ক
    0.54
    ig
    0.54
    sh
    0.51
    ch
    0.50
    s
    0.50
    POSITIVE LOGITS
    迎え
    0.51
    嚥
    0.49
    крови
    0.49
    корд
    0.49
    JKL
    0.47
    крытие
    0.47
    entiary
    0.46
    हो
    0.46
    育て
    0.46
    ቮ
    0.46
    Activations Density 0.000%

    No Known Activations