© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 12459
    Prev
    Next
    INDEX
    Explanations

    automatic or default actions

    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_24_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
    𝑫
    0.82
     활용
    0.77
     경영
    0.75
     목표
    0.73
    𝑪
    0.71
    CuO
    0.70
    ান্তি
    0.70
    𝑭
    0.69
    𝑺
    0.68
     분야
    0.68
    POSITIVE LOGITS
     automaticamente
    1.17
     automatically
    1.13
     автоматически
    1.13
     automatic
    1.07
     default
    1.05
     automáticamente
    1.05
     automatisch
    1.05
    自动
    1.02
     automatiquement
    1.01
     Automatically
    0.92
    Activations Density 0.009%

    No Known Activations