© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40389
    Prev
    Next
    INDEX
    Explanations

    German novels

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

    customer interactions

    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
    сій
    0.48
    哩
    0.45
    лі
    0.44
    睽
    0.43
    ಧಾರವಾಡ
    0.43
    該
    0.43
    旅客
    0.42
    蜂
    0.42
     kaos
    0.42
    elan
    0.41
    POSITIVE LOGITS
     χρησιμοποι
    0.55
     fraternal
    0.54
     흥
    0.50
     exerce
    0.49
     выделить
    0.49
     ο
    0.48
     impug
    0.48
     와
    0.48
     excitatory
    0.48
     믿
    0.48
    Activations Density 0.000%

    No Known Activations