© 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. 180383
    Prev
    Next
    INDEX
    Explanations

    Pierce describes

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

    impact and consequences

    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
    dob
    0.47
    贫
    0.46
    individual
    0.43
    decorative
    0.43
    ampo
    0.43
    Anglo
    0.41
    貧
    0.40
    伯
    0.39
    纪
    0.39
    nob
    0.38
    POSITIVE LOGITS
    ড়ান্ত
    0.50
     monstru
    0.48
     przypadku
    0.47
    ciąż
    0.46
     stesso
    0.46
     vetro
    0.45
     മികച്ച
    0.44
     downregulation
    0.44
     miatt
    0.44
     zuverläss
    0.44
    Activations Density 0.002%

    No Known Activations