© 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. 3546
    Prev
    Next
    INDEX
    Explanations

    growth, working, influences, accuracy

    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
     pertanyaan
    0.80
     スカート
    0.77
     ótima
    0.77
     perguntas
    0.75
    
    0.73
    <0x88>
    0.72
    ješt
    0.72
     comentários
    0.72
    ॕ
    0.72
    <0x86>
    0.71
    POSITIVE LOGITS
    with
    0.80
     with
    0.72
     Emergency
    0.68
    тори
    0.68
    上下
    0.66
    ल
    0.66
    дяки
    0.65
    ค่า
    0.65
     anyhow
    0.65
     자
    0.64
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.