© 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. 210698
    Prev
    Next
    INDEX
    Explanations

    descriptive nouns

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

    reference to following "keep"

    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
     змі
    0.54
     зміню
    0.53
    க்கழக
    0.49
     mencegah
    0.49
    iculate
    0.47
     nonlocal
    0.47
    寧
    0.47
     asympt
    0.47
     thresh
    0.47
     चित
    0.47
    POSITIVE LOGITS
    Fonts
    0.50
    ?:
    0.47
    Structure
    0.47
    Office
    0.46
    !:
    0.46
    Cell
    0.45
     Structure
    0.44
    *:
    0.44
    输出
    0.43
    Boards
    0.42
    Activations Density 0.003%

    No Known Activations