© 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. 185276
    Prev
    Next
    INDEX
    Explanations

    action adventure films

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

    average squared deviation

    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
     cit
    0.47
    Opens
    0.45
    Medit
    0.44
     transistor
    0.44
    는
    0.44
     محسوس
    0.42
     سبيل
    0.42
     circumvent
    0.42
     permeates
    0.42
     ostensibly
    0.41
    POSITIVE LOGITS
     lão
    0.54
    ાલ
    0.46
    বড়
    0.46
    ול
    0.46
    лять
    0.45
    প্ত
    0.44
     niemand
    0.44
     বড়
    0.43
     детали
    0.43
    Ｌ
    0.43
    Activations Density 0.000%

    No Known Activations