© 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. 48468
    Prev
    Next
    INDEX
    Explanations

    questions and explanations

    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
     uzn
    0.46
     veterin
    0.44
    izuje
    0.44
     funda
    0.41
    iani
    0.41
     texte
    0.41
     tib
    0.40
     fowl
    0.40
    +]
    0.40
     universitet
    0.40
    POSITIVE LOGITS
    Location
    0.47
     trò
    0.46
     confond
    0.44
     Саша
    0.44
    ப்
    0.44
    ্রিক
    0.43
     is
    0.42
    arle
    0.41
    Primary
    0.41
    先
    0.40
    Activations Density 0.003%

    No Known Activations