© 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. 3093
    Prev
    Next
    INDEX
    Explanations

    connecting concepts or actions

    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
    ل
    0.56
    Dire
    0.55
    Examples
    0.47
    an
    0.47
    ش
    0.47
    ל
    0.46
    Location
    0.45
    Standard
    0.45
    Khan
    0.44
    DID
    0.43
    POSITIVE LOGITS
    ៧
    0.56
     contradictions
    0.50
     scathing
    0.48
    ៦
    0.48
     :");
    0.46
     répart
    0.46
     fractures
    0.46
     구매
    0.46
    ၆
    0.44
     мнение
    0.44
    Activations Density 0.001%

    No Known Activations