© 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. 205825
    Prev
    Next
    INDEX
    Explanations

    defining categories and intents

    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
     dessas
    0.52
    ف
    0.47
     dentro
    0.45
    生地
    0.44
    ς
    0.44
    만을
    0.44
    쉐
    0.44
    на
    0.43
    advert
    0.43
     முற்ற
    0.43
    POSITIVE LOGITS
    o
    0.45
    ැබ
    0.45
    och
    0.43
     parked
    0.43
     youngest
    0.43
     Bharatiya
    0.43
    ozygous
    0.42
    liers
    0.42
    ridas
    0.42
     ఘ
    0.41
    Activations Density 0.002%

    No Known Activations