© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 193386
    Prev
    Next
    INDEX
    Explanations

    progress and prosperity

    np_acts-logits-general · gemini-2.5-flash-lite

    Linux, bags, examples, anywhere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    骋
    0.46
     oftentimes
    0.45
    Step
    0.44
    Hav
    0.43
    वीं
    0.43
    Andrews
    0.43
    ेंस
    0.42
    Haven
    0.42
    সি
    0.42
    Honestly
    0.42
    POSITIVE LOGITS
     Pampl
    0.63
     Bakufu
    0.52
     bay
    0.51
     Librarian
    0.49
     劉
    0.49
    rocyte
    0.48
    zyloxy
    0.47
     Dying
    0.47
     Yukawa
    0.47
     Employee
    0.46
    Activations Density 0.001%

    No Known Activations