© 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. 192624
    Prev
    Next
    INDEX
    Explanations

    listen and well

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

    technical and conceptual connections

    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
     aphids
    0.48
     ಬಿ
    0.44
     deficits
    0.43
     feb
    0.42
     hires
    0.42
    ▌
    0.42
     frontage
    0.41
     [\
    0.41
     megs
    0.40
     plus
    0.39
    POSITIVE LOGITS
     มัน
    0.46
    Array
    0.44
     gratification
    0.42
    rapport
    0.42
    sizeof
    0.41
     หัว
    0.41
    ään
    0.41
    odym
    0.41
    чению
    0.41
    䣰
    0.40
    Activations Density 0.000%

    No Known Activations