© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44366
    Prev
    Next
    INDEX
    Explanations

    books, machines, and understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     blod
    0.41
    IT
    0.41
    embro
    0.41
     bt
    0.41
     szczegól
    0.41
    array
    0.40
    |)
    0.39
    攽
    0.39
     बट
    0.39
    š
    0.39
    POSITIVE LOGITS
     permitió
    0.51
    ouvement
    0.48
     便利
    0.48
     permitirá
    0.46
     SERVICE
    0.46
     Tianjin
    0.46
     પ્રો
    0.45
    ClN
    0.45
     RATE
    0.45
     గ్ర
    0.45
    Activations Density 0.001%

    No Known Activations