© 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. 62122
    Prev
    Next
    INDEX
    Explanations

    employment, Kodak, variety, main, centralized

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

    CREATE TABLE

    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
    Dem
    0.42
    筠
    0.41
    azi
    0.40
    ier
    0.39
     alphabet
    0.39
    Fel
    0.39
     apartment
    0.39
     espada
    0.39
     condo
    0.38
     unheard
    0.38
    POSITIVE LOGITS
     ',
    0.52
    prit
    0.51
     liegen
    0.48
    نون
    0.48
     Франции
    0.47
     goodies
    0.47
    ス
    0.47
     allons
    0.46
     ROC
    0.46
     ejection
    0.46
    Activations Density 0.000%

    No Known Activations