© 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. 31691
    Prev
    Next
    INDEX
    Explanations

    predicted

    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
    Negative Logits
     erasing
    0.50
     quantization
    0.50
    さまざまな
    0.50
     coils
    0.49
     multicolored
    0.49
     decomposition
    0.48
     deformations
    0.47
    decomposition
    0.46
    <0x8A>
    0.46
     tattoos
    0.45
    POSITIVE LOGITS
     कानून
    0.52
     रेगु
    0.50
    权力
    0.49
     القانون
    0.47
     कंटिन्यू
    0.47
    官员
    0.45
     konstit
    0.45
     menyatakan
    0.44
     citoyens
    0.44
     वकील
    0.44
    Activations Density 0.011%

    No Known Activations