© 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. 40666
    Prev
    Next
    INDEX
    Explanations

    expect. *

    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
    ක
    0.87
    പാടി
    0.83
    chen
    0.79
    व
    0.78
    ober
    0.71
    orgung
    0.71
    处罚
    0.71
     chipped
    0.68
     desag
    0.68
     Schönheit
    0.68
    POSITIVE LOGITS
    ю
    0.82
    ваны
    0.81
     leaps
    0.79
     яго
    0.78
    不由
    0.76
    ीजन
    0.75
    рень
    0.74
    рию
    0.74
    ।'
    0.73
    🜨
    0.73
    Activations Density 0.000%

    No Known Activations