© 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-65K
    7. 61322
    Prev
    Next
    INDEX
    Explanations

    -related suffixes and terms

    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_65k_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
    S
    0.50
    UtcNow
    0.48
    J
    0.46
    Favourite
    0.44
    σετε
    0.43
    ১
    0.43
    '.$
    0.43
    ιού
    0.42
    ল
    0.42
    Ự
    0.42
    POSITIVE LOGITS
    amiento
    0.47
    ificante
    0.45
    avelmente
    0.45
     نحن
    0.45
     никогда
    0.45
    에서도
    0.44
    дето
    0.43
     نح
    0.42
     مال
    0.42
     nunca
    0.42
    Activations Density 0.020%

    No Known Activations