© 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. 22884
    Prev
    Next
    INDEX
    Explanations

    clips, white, 3, bubble, valleys, Orbit, clip, boxes, App

    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
    ل
    0.73
     واس
    0.55
    وب
    0.55
    Smoking
    0.54
    به
    0.53
    馬
    0.53
     ن
    0.52
    ام
    0.51
    ح
    0.51
    د
    0.50
    POSITIVE LOGITS
    ról
    0.48
     Claude
    0.44
    tsz
    0.43
    nicy
    0.43
    atthena
    0.43
     BW
    0.42
    ilien
    0.42
     transcendence
    0.41
     প্রসঙ্গে
    0.41
    ąpi
    0.41
    Activations Density 0.000%

    No Known Activations