© 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. 35738
    Prev
    Next
    INDEX
    Explanations

    owned by

    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
    क
    1.58
     understandably
    1.55
    硋
    1.36
    あります
    1.34
    おり
    1.27
    ী
    1.26
     freel
    1.23
    ский
    1.22
    ciplinary
    1.21
    दायक
    1.21
    POSITIVE LOGITS
    м
    2.31
    ar
    2.23
    m
    2.13
    toluene
    2.11
    ir
    2.00
    iak
    1.98
    iendo
    1.97
    ون
    1.95
    ol
    1.88
    و
    1.86
    Activations Density 0.004%

    No Known Activations