© 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. 159687
    Prev
    Next
    INDEX
    Explanations

    cases or visitors

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

    specialist, types, mean, market in

    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
    obiettivo
    0.45
    ListItem
    0.44
     চলতে
    0.44
    Unter
    0.43
    אם
    0.43
    ONDER
    0.43
    𝘆
    0.43
    AppendLine
    0.42
     சாலை
    0.42
    ylidene
    0.42
    POSITIVE LOGITS
     পোষণ
    0.50
     which
    0.47
     penguins
    0.46
     Hong
    0.43
     Scrolls
    0.43
     cases
    0.43
    1
    0.43
    ‌ها
    0.43
     ats
    0.43
     mosaics
    0.42
    Activations Density 0.000%

    No Known Activations