© 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. 72710
    Prev
    Next
    INDEX
    Explanations

    finding articles or options

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

    standard input/output redirection

    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
    uram
    0.52
    ៍
    0.49
    ᱙
    0.49
    redu
    0.48
    dri
    0.47
     スリム
    0.46
    ථා
    0.46
    ทยาลัย
    0.45
     значение
    0.45
    incorrect
    0.45
    POSITIVE LOGITS
     Neuroscience
    0.46
     guardianship
    0.45
    吲
    0.44
     Frontiers
    0.44
     Guilford
    0.42
    Ņ
    0.42
     semangat
    0.41
     prospective
    0.41
     Guardians
    0.41
     Prospective
    0.41
    Activations Density 0.000%

    No Known Activations