© 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. 220121
    Prev
    Next
    INDEX
    Explanations

    invade commercial

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

    indicators and specific information

    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
    umboldt
    0.50
     adhering
    0.50
    ර
    0.47
    挀
    0.47
    ት
    0.46
    ಿರ
    0.46
     micrograms
    0.46
     milligrams
    0.46
    ٴ
    0.46
     harmonica
    0.45
    POSITIVE LOGITS
    KILL
    0.51
    Vine
    0.48
    ﻔ
    0.45
    ovation
    0.45
     कृ
    0.44
    ology
    0.43
    भूत
    0.43
    comput
    0.42
     trecut
    0.42
     asesin
    0.42
    Activations Density 0.001%

    No Known Activations