© 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. 130290
    Prev
    Next
    INDEX
    Explanations

    more than

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

    definitive answers, information, wisdom

    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
    托
    0.46
    קט
    0.42
    กำ
    0.40
    ือง
    0.40
    جلد
    0.40
    ээр
    0.40
    脩
    0.40
    áv
    0.39
    เมตร
    0.39
     bund
    0.39
    POSITIVE LOGITS
    abbati
    0.52
     impulsive
    0.50
    yta
    0.50
     marzo
    0.48
    unches
    0.48
     exhort
    0.47
     outcrops
    0.47
    रिक्
    0.47
     divisive
    0.46
     お客様
    0.46
    Activations Density 0.000%

    No Known Activations