© 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. 35341
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

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

    specific computer terms

    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
    জ
    0.64
    ोत
    0.58
    ні
    0.55
    ्वे
    0.55
     enfoc
    0.54
     enunci
    0.54
     indelible
    0.53
     empat
    0.53
    شع
    0.53
    f
    0.53
    POSITIVE LOGITS
    3
    0.64
    4
    0.64
    MSFontService
    0.63
    _{
    0.63
    1
    0.63
     لیے
    0.62
    -_
    0.60
     Германия
    0.59
    \{-\
    0.57
     for
    0.55
    Activations Density 0.013%

    No Known Activations