© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 67980
    Prev
    Next
    INDEX
    Explanations

    Reviews is, mile of, this classic, edge policy

    np_acts-logits-general · gemini-2.5-flash-lite

    destroyed breeds, dataset describes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     simply
    0.49
    arth
    0.49
     everyone
    0.47
    rektor
    0.46
    ]])
    0.46
    んで
    0.46
     seeing
    0.45
     discovered
    0.45
     deploying
    0.45
    simply
    0.45
    POSITIVE LOGITS
    னு
    0.47
    榆
    0.46
    بھی
    0.46
     Petroleum
    0.46
     Elat
    0.46
     Lipid
    0.45
    Integrated
    0.44
    黠
    0.44
    Importance
    0.44
     hong
    0.43
    Activations Density 0.000%

    No Known Activations