© 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. 92546
    Prev
    Next
    INDEX
    Explanations

    lists followed by specific terms

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

    completed or finished actions

    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
     dalších
    0.47
     ልዩ
    0.45
    BlackRatingDiff
    0.44
     유사
    0.44
     필
    0.43
     також
    0.42
     גם
    0.42
     ఇతర
    0.42
     ዓይነ
    0.42
    ด
    0.42
    POSITIVE LOGITS
    न्होंने
    0.50
    din
    0.50
    ade
    0.46
     perlu
    0.46
     complet
    0.46
    うちに
    0.45
    য়া
    0.45
     இடையே
    0.45
     jste
    0.44
    dan
    0.43
    Activations Density 0.000%

    No Known Activations