© 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. 176992
    Prev
    Next
    INDEX
    Explanations

    sequences ending in common words

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

    quick updates, smaller file, helpers get

    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
    vasive
    0.45
     criteri
    0.44
    Église
    0.43
    🥫
    0.43
    trusted
    0.42
    ່ນ
    0.42
    㵄
    0.42
    sess
    0.42
     অত্যন্ত
    0.41
     기준
    0.41
    POSITIVE LOGITS
     pís
    0.49
     Schrift
    0.49
     Verbindung
    0.48
    ท
    0.47
     zaradi
    0.46
     pozw
    0.46
     About
    0.46
    rifft
    0.45
     zapis
    0.45
     kog
    0.45
    Activations Density 0.001%

    No Known Activations