© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 324
    Prev
    Next
    INDEX
    Explanations

    empty input

    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_12_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
    THING
    0.73
    𝐬
    0.72
    ्स
    0.64
    signale
    0.58
    পি
    0.56
    electrolyte
    0.55
    więks
    0.55
     către
    0.54
    𝐞
    0.52
    ности
    0.52
    POSITIVE LOGITS
    на
    0.81
    न
    0.79
    ان
    0.78
    ية
    0.64
    কে
    0.63
    ন
    0.62
    ੇ
    0.60
    ور
    0.57
    ний
    0.57
    م
    0.57
    Activations Density 0.241%

    No Known Activations