© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7807
    Prev
    Next
    INDEX
    Explanations

    normally, typically, usually

    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
     Fruit
    0.42
     Christopher
    0.42
     hinsichtlich
    0.42
    られました
    0.40
     Nothing
    0.39
     کامیابی
    0.39
     Pixel
    0.39
    㗊
    0.38
     accompagné
    0.38
    Traversal
    0.38
    POSITIVE LOGITS
    通常
    0.66
     typically
    0.64
     normally
    0.64
     ordinarily
    0.63
    normally
    0.63
     usually
    0.61
     normalerweise
    0.59
     обычно
    0.56
    usually
    0.55
    typically
    0.54
    Activations Density 0.104%

    No Known Activations