© 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. 105912
    Prev
    Next
    INDEX
    Explanations

    Location: Iowa City

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

    explanation of concepts

    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
     zuten
    0.48
    Hen
    0.48
     Hen
    0.46
    戰
    0.45
    保护
    0.45
    漂亮的
    0.44
    fohlen
    0.44
    Arte
    0.43
    Holmes
    0.42
     красиво
    0.42
    POSITIVE LOGITS
     concurring
    0.53
     retrospect
    0.49
     SISO
    0.46
     examin
    0.46
    =-\
    0.45
     milling
    0.45
     misconceptions
    0.44
     boredom
    0.44
     egent
    0.44
    `]
    0.43
    Activations Density 0.000%

    No Known Activations