© 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. 35896
    Prev
    Next
    INDEX
    Explanations

    performance and training skills

    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
     отды
    0.76
    )</
    0.75
     cooldown
    0.73
     لإ
    0.71
    ).</
    0.71
     
    0.71
     মর
    0.70
     неу
    0.70
     
    0.70
     to
    0.69
    POSITIVE LOGITS
     ballerina
    0.96
     ballet
    0.90
     acrob
    0.86
     acrobat
    0.86
     gymnast
    0.85
    表演
    0.84
     soloist
    0.83
     dancer
    0.82
     Escola
    0.79
    ز
    0.76
    Activations Density 0.073%

    No Known Activations