© 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. 178255
    Prev
    Next
    INDEX
    Explanations

    second round

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

    Don't just read

    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
     volo
    0.47
    urgent
    0.46
     litigants
    0.46
     demean
    0.46
     በፍ
    0.45
     examine
    0.44
    VALID
    0.44
     hyperlink
    0.44
     congratulate
    0.43
    ').':
    0.43
    POSITIVE LOGITS
     Monkeys
    0.50
    ́ng
    0.49
    ίκ
    0.45
    ρα
    0.45
    скопа
    0.44
    λ
    0.44
    節
    0.43
     Atlético
    0.43
    скус
    0.43
     Stopping
    0.42
    Activations Density 0.001%

    No Known Activations