© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 9088
    Prev
    Next
    INDEX
    Explanations

    div followed by class

    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
    오
    0.97
    K
    0.96
    아
    0.93
    人都
    0.88
    ک
    0.87
    。
    0.87
    꿉
    0.85
    ۹
    0.85
     aumentó
    0.80
    ہ
    0.79
    POSITIVE LOGITS
    ва
    0.78
    0.75
    ться
    0.73
    ը
    0.73
     neurotic
    0.72
     plex
    0.71
    зм
    0.71
     khas
    0.70
    te
    0.69
    stin
    0.69
    Activations Density 0.000%

    No Known Activations