© 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-16K
    7. 11946
    Prev
    Next
    INDEX
    Explanations

    sheets and linen

    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_16k_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
    ian
    1.35
    م
    1.30
    ح
    1.27
    र
    1.26
    ش
    1.13
     gingen
    1.12
    itionally
    1.10
    வுக்கு
    1.10
    ो
    1.10
    िया
    1.09
    POSITIVE LOGITS
    TA
    1.04
     quisquam
    1.04
    ї
    1.02
    йл
    1.02
     zest
    0.97
    AE
    0.95
    LANG
    0.95
    arzt
    0.95
     commenc
    0.93
     Воз
    0.92
    Activations Density 0.019%

    No Known Activations