© 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. 42046
    Prev
    Next
    INDEX
    Explanations

    quantifiers and indicators

    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
    ي
    0.87
    ی
    0.86
    y
    0.85
    ా
    0.84
    a
    0.82
    <0x0D>
    0.78
    ר
    0.78
    "
    0.77
    ت
    0.76
    र
    0.75
    POSITIVE LOGITS
     үз
    0.96
     nke
    0.96
     koje
    0.92
     โอเค
    0.88
    үз
    0.85
    шымта
    0.84
     phấn
    0.83
    irán
    0.82
     kỳ
    0.81
     crítico
    0.81
    Activations Density 0.000%

    No Known Activations