© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 42598
    Prev
    Next
    INDEX
    Explanations

    plots or analysis

    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
    ו
    1.00
    o
    0.95
    л
    0.88
     Під
    0.84
    ┍
    0.81
    電車
    0.79
     Improvements
    0.79
    亠
    0.79
    㐄
    0.79
     під
    0.79
    POSITIVE LOGITS
    افظ
    0.84
     posteriores
    0.75
    Contain
    0.73
     equivalente
    0.73
    is
    0.70
     ander
    0.69
    ly
    0.68
    At
    0.68
     astray
    0.68
     erset
    0.68
    Activations Density 0.000%

    No Known Activations