© 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. 103504
    Prev
    Next
    INDEX
    Explanations

    mentioning future actions

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

    causes and regimen compliance

    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
    3
    0.49
     dicembre
    0.47
    feb
    0.43
     totalSupply
    0.42
    ovania
    0.42
     mercredi
    0.42
    kons
    0.41
    afe
    0.41
     नव्ह
    0.40
    manam
    0.40
    POSITIVE LOGITS
    ،
    0.55
     patterned
    0.50
     dermatologist
    0.50
     regimen
    0.49
     Jama
    0.49
    并且
    0.49
     기준
    0.47
     기준으로
    0.46
     hoặc
    0.46
     প্রত্যেক
    0.46
    Activations Density 0.000%

    No Known Activations