© 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
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1537
    Prev
    Next
    INDEX
    Explanations

    maintain, create, or change

    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
    Mere
    0.77
    ORES
    0.75
    实质
    0.72
    AcOH
    0.71
    <0x80>
    0.70
     GK
    0.69
    ВС
    0.69
    OTROS
    0.69
    り
    0.68
    굳
    0.68
    POSITIVE LOGITS
     spoloč
    0.76
    ure
    0.76
    ilene
    0.74
    hoe
    0.74
     çocuk
    0.73
    ia
    0.72
     tertarik
    0.72
    iny
    0.71
     Runner
    0.71
    ashion
    0.71
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.