© 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. 81572
    Prev
    Next
    INDEX
    Explanations

    company name or subject

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

    you like/love/feel like

    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
    Consistency
    0.47
     किससे
    0.42
    叟
    0.42
    ToList
    0.42
     разрабаты
    0.40
    Lisa
    0.39
     Deane
    0.39
     डूब
    0.38
    Chen
    0.38
     பொருந்த
    0.38
    POSITIVE LOGITS
     millió
    0.42
     groei
    0.41
    很简单
    0.40
     degenerative
    0.40
    infl
    0.39
     stö
    0.38
     Ä
    0.37
    কেশন
    0.37
     fascist
    0.37
    ционный
    0.37
    Activations Density 0.000%

    No Known Activations