© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75588
    Prev
    Next
    INDEX
    Explanations

    celebrated events, book details, conditioning, goals, numbers

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

    Seller, Buyer, or technical descriptions

    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
    Negative Logits
    𒂵
    0.47
    cuando
    0.46
     atheist
    0.46
     Versand
    0.44
    އް
    0.43
    ceral
    0.43
    )}/>
    0.43
    Გ
    0.43
     és
    0.43
     agentes
    0.43
    POSITIVE LOGITS
    тус
    0.53
    to
    0.50
    i
    0.50
     пер
    0.48
    composable
    0.48
    then
    0.46
    OK
    0.45
     двох
    0.44
    OSED
    0.44
     наступ
    0.44
    Activations Density 0.000%

    No Known Activations