© 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. 16333
    Prev
    Next
    INDEX
    Explanations

    near future

    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
     Style
    0.60
    Style
    0.60
     Severity
    0.55
    тэ
    0.53
    գ
    0.53
    padding
    0.52
    ####
    0.52
     Lever
    0.51
    ve
    0.50
    >>>>
    0.50
    POSITIVE LOGITS
    issimi
    0.86
    shoring
    0.84
     unanim
    0.77
    shore
    0.76
    issimo
    0.73
     قریب
    0.70
     misses
    0.69
     toekomst
    0.69
     futuro
    0.68
    َا
    0.68
    Activations Density 0.059%

    No Known Activations