© 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. 223137
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    external/internal states

    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
    ण्यात
    0.50
    ত
    0.48
    рил
    0.46
    diabetes
    0.46
    тки
    0.45
    нки
    0.44
    ebra
    0.44
    २०
    0.44
    шается
    0.44
    ebar
    0.43
    POSITIVE LOGITS
     Martyrs
    0.42
     agitation
    0.42
     ભ
    0.40
     ně
    0.40
     انه
    0.40
     HUGE
    0.40
     inici
    0.39
     ആക്രമ
    0.39
     vehemently
    0.38
     některé
    0.38
    Activations Density 0.001%

    No Known Activations