© 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. 10776
    Prev
    Next
    INDEX
    Explanations

    understanding

    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
    ن
    1.70
    ა
    1.64
    니다
    1.63
    ский
    1.62
    তে
    1.57
    υτό
    1.52
    đer
    1.48
    ется
    1.47
    ే
    1.44
    니
    1.43
    POSITIVE LOGITS
    motiv
    1.91
    d
    1.91
    prints
    1.91
    kannya
    1.91
    liness
    1.80
    pants
    1.80
    lay
    1.73
    lists
    1.73
    hots
    1.73
    lat
    1.72
    Activations Density 0.046%

    No Known Activations