© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205589
    Prev
    Next
    INDEX
    Explanations

    procedure or dependency definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     तहसील
    0.50
    방송
    0.48
    يسي
    0.48
     आकार
    0.47
    缆
    0.46
    潵
    0.46
    Attenuation
    0.44
    ình
    0.43
    inese
    0.43
    ИС
    0.43
    POSITIVE LOGITS
     for
    0.50
    dorf
    0.46
     mil
    0.45
     or
    0.44
    functie
    0.44
     mill
    0.44
    M
    0.43
     house
    0.43
    house
    0.43
    accep
    0.43
    Activations Density 0.003%

    No Known Activations