© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35992
    Prev
    Next
    INDEX
    Explanations

    physical appearance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ie
    0.93
     eight
    0.83
     keeper
    0.83
    োদ্ধ
    0.80
    ș
    0.80
    
    0.79
     Cambodian
    0.78
    formance
    0.78
     Southwest
    0.78
    up
    0.77
    POSITIVE LOGITS
     사항
    0.82
     간단
    0.82
    着
    0.79
    ﻬ
    0.79
    元気
    0.77
    께
    0.77
    ..--
    0.75
    ।*
    0.75
    나는
    0.74
    нта
    0.73
    Activations Density 0.000%

    No Known Activations