© 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. 3953
    Prev
    Next
    INDEX
    Explanations

    pandas groupby

    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
     obie
    1.05
     cuadr
    0.93
    hkar
    0.91
     évalu
    0.91
     desist
    0.88
     Government
    0.88
    ない
    0.86
    哣
    0.86
     cambi
    0.86
     Governo
    0.85
    POSITIVE LOGITS
    ת
    1.01
     또한
    0.99
    ти
    0.95
    вающий
    0.88
    est
    0.86
    에서
    0.85
    give
    0.84
    сы
    0.82
    はもちろん
    0.80
    cop
    0.80
    Activations Density 0.001%

    No Known Activations