© 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. 170391
    Prev
    Next
    INDEX
    Explanations

    Unreal, unicorn, data

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

    possibilities and intel

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ಪ್ರಯೋಜನ
    0.51
    깅
    0.47
     returnPacket
    0.47
    즈
    0.46
     треть
    0.45
    ̾
    0.45
    ActionPerformed
    0.45
     сочета
    0.45
    lač
    0.45
    queous
    0.44
    POSITIVE LOGITS
     andre
    0.58
     Drift
    0.54
     Unreal
    0.52
     Unicorn
    0.52
    AW
    0.49
    データ
    0.48
    Ricardo
    0.48
    unicorn
    0.47
    data
    0.47
    n
    0.47
    Activations Density 0.000%

    No Known Activations