© 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. 213461
    Prev
    Next
    INDEX
    Explanations

    can have, will recognize

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

    predicting outcomes based on data

    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
    }{-
    0.48
     Nullam
    0.47
    fü
    0.46
    াবলীর
    0.46
     tubes
    0.45
     divergents
    0.45
    স্‌
    0.44
    sten
    0.43
     ஜ
    0.43
     bakter
    0.43
    POSITIVE LOGITS
    乡村
    0.45
    communities
    0.43
     গ্রামা
    0.43
    きっと
    0.42
     SVP
    0.42
    高校
    0.42
    ఓ
    0.42
    堌
    0.41
     गांवों
    0.41
    過程
    0.40
    Activations Density 0.001%

    No Known Activations