© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 2759
    Prev
    Next
    INDEX
    Explanations

    source field, low complexity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aná
    0.95
    蛟
    0.73
    featuring
    0.72
     compleja
    0.69
     elétrica
    0.68
    uity
    0.67
     procé
    0.67
     jsme
    0.66
    恹
    0.66
    电
    0.66
    POSITIVE LOGITS
    Move
    0.82
     fucking
    0.78
    LAND
    0.77
    Strings
    0.74
     directories
    0.73
    صير
    0.72
     MOV
    0.72
    Rise
    0.72
    الصفحه
    0.71
     sodass
    0.69
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.