© 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. 10630
    Prev
    Next
    INDEX
    Explanations

    writing about development

    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
     edifice
    1.62
    الان
    1.56
    ت
    1.55
    eers
    1.52
    رو
    1.44
    o
    1.44
    야
    1.41
    Neue
    1.38
    КП
    1.37
    ו
    1.34
    POSITIVE LOGITS
    د
    1.70
    is
    1.68
    it
    1.62
    isesti
    1.55
    ios
    1.51
    ี
    1.50
    ats
    1.49
     apabila
    1.48
    itto
    1.45
    並且
    1.45
    Activations Density 0.060%

    No Known Activations