© 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. 205472
    Prev
    Next
    INDEX
    Explanations

    technical concepts and quantities

    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
    Not in Any Lists

    No Comments

    Negative Logits
     正
    0.48
     cursory
    0.45
     草
    0.44
     ง
    0.44
    క్సి
    0.44
    AMP
    0.43
    菟
    0.43
    tDBOutput
    0.43
     catast
    0.43
    డియో
    0.42
    POSITIVE LOGITS
    \
    0.62
     residues
    0.46
     assemblies
    0.46
    ates
    0.46
     derivatives
    0.46
     accents
    0.46
     moulds
    0.45
     flavours
    0.44
     appoints
    0.44
    romes
    0.44
    Activations Density 0.002%

    No Known Activations