© 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. 136264
    Prev
    Next
    INDEX
    Explanations

    Basmati, Jasmine

    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
     ಸುತ್ತ
    0.52
     хро
    0.52
     стали
    0.50
     జ
    0.50
     అత
    0.49
    <unused2115>
    0.48
     коли
    0.48
     постро
    0.48
     כל
    0.47
     были
    0.47
    POSITIVE LOGITS
    IS
    0.56
    <!
    0.56
    validation
    0.53
    OS
    0.52
    MD
    0.49
    refresh
    0.49
    input
    0.48
    PRO
    0.48
    USE
    0.46
    Cont
    0.46
    Activations Density 0.002%

    No Known Activations