© 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. 108635
    Prev
    Next
    INDEX
    Explanations

    pre fall fashion

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

    specific topics and jargon

    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
     criminality
    0.56
     quarant
    0.51
     election
    0.50
    낑
    0.50
     probation
    0.47
     persona
    0.46
     probationary
    0.46
     adolesc
    0.46
     belliger
    0.45
     respecto
    0.45
    POSITIVE LOGITS
     ರಚ
    0.53
    镂
    0.49
    SuppressWarnings
    0.49
    揭
    0.45
    fashioned
    0.45
     архе
    0.44
    考古
    0.44
    箓
    0.43
    uted
    0.43
     Fourier
    0.43
    Activations Density 0.000%

    No Known Activations