© 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. 70863
    Prev
    Next
    INDEX
    Explanations

    legal clauses and conditions

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

    say we're

    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
    Not in Any Lists

    No Comments

    Negative Logits
    【
    0.47
    chets
    0.44
     모습을
    0.44
     पहलुओं
    0.42
    信心
    0.41
     दृष्टिकोण
    0.40
     모습
    0.40
     【
    0.40
    未知
    0.40
    olim
    0.40
    POSITIVE LOGITS
    uhà
    0.50
     veya
    0.48
    participant
    0.47
     มั้ย
    0.47
    वण्यात
    0.46
    গ্র
    0.45
    きたい
    0.45
     condam
    0.45
     いや
    0.44
    विण्यात
    0.44
    Activations Density 0.006%

    No Known Activations