© 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. 99220
    Prev
    Next
    INDEX
    Explanations

    authors and contemporary design

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

    glass, compression, electrode

    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
    وسیع
    0.51
    vective
    0.47
    onian
    0.47
    лькі
    0.46
    urgence
    0.46
    erved
    0.46
    وله
    0.46
    庁
    0.46
    ^{*}(\
    0.46
    бліоте
    0.45
    POSITIVE LOGITS
     automat
    0.54
     kapp
    0.52
     CodeableConcept
    0.51
     zat
    0.51
     Karm
    0.51
     a
    0.50
     diplomat
    0.49
     assist
    0.49
     ergonomics
    0.48
     aid
    0.48
    Activations Density 0.000%

    No Known Activations