© 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. 40-GEMMASCOPE-2-RES-262K
    7. 130275
    Prev
    Next
    INDEX
    Explanations

    means, size, consequences

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    bx
    0.46
    ädchen
    0.43
    cip
    0.43
    roman
    0.40
    Az
    0.40
    мей
    0.39
    ༽
    0.38
    bcc
    0.37
    dip
    0.37
    cstr
    0.36
    POSITIVE LOGITS
     pioneer
    0.50
     delegate
    0.46
     pioneering
    0.44
     pione
    0.44
     founding
    0.41
    गैर
    0.41
     (\$
    0.39
     партнер
    0.39
     pioneers
    0.39
     non
    0.38
    Activations Density 0.000%

    No Known Activations