© 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-16K
    7. 13275
    Prev
    Next
    INDEX
    Explanations

    code blocks or program errors

    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_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
    l
    0.93
    p
    0.89
    tion
    0.83
     n
    0.80
     breakpoints
    0.77
    n
    0.77
    ર
    0.77
    コレート
    0.75
    k
    0.75
    pus
    0.75
    POSITIVE LOGITS
    ရေး
    0.91
     cadeira
    0.75
    ละคร
    0.75
     सम्मान
    0.73
     майже
    0.73
     завжди
    0.72
     добре
    0.72
    Theater
    0.72
    cherry
    0.71
    裁判
    0.71
    Activations Density 0.000%

    No Known Activations