© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1283
    Prev
    Next
    INDEX
    Explanations

    за- prefix

    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_31_width_16k_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
    unya
    0.50
     ঠিক
    0.47
    一直在
    0.46
    域
    0.46
     信
    0.46
    ี่ย
    0.45
    ວິ
    0.45
     agu
    0.45
     agh
    0.45
    状
    0.43
    POSITIVE LOGITS
    пря
    0.63
    За
    0.61
    будь
    0.60
    trk
    0.57
     zast
    0.57
    Closed
    0.57
     zakl
    0.57
     За
    0.56
     zap
    0.56
     предела
    0.56
    Activations Density 0.014%

    No Known Activations