© 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. 128260
    Prev
    Next
    INDEX
    Explanations

    ** " couch

    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
    ção
    0.52
    os
    0.50
    ಞ
    0.50
    omy
    0.49
    ello
    0.45
    ombasa
    0.44
     loses
    0.44
    _{\
    0.43
    ière
    0.43
    ors
    0.43
    POSITIVE LOGITS
    た
    0.44
     cliquer
    0.44
    ぬ
    0.43
     fakat
    0.42
     ווא
    0.41
    Pentru
    0.41
     ವಿವಿಧ
    0.40
     महत्
    0.40
    クリック
    0.40
    憤
    0.40
    Activations Density 0.001%

    No Known Activations