© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 161050
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, and places

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

    character design and theatrical elements

    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
    ا
    0.57
    체
    0.56
    älle
    0.55
    어
    0.50
    ટ
    0.49
    บ
    0.48
    او
    0.48
    종
    0.46
    اءِ
    0.45
    グ
    0.45
    POSITIVE LOGITS
     সমান
    0.45
     serat
    0.45
     July
    0.45
     viii
    0.45
     XXIV
    0.43
     Writing
    0.43
    TextStyle
    0.42
     циф
    0.41
    くだ
    0.40
    xii
    0.40
    Activations Density 0.000%

    No Known Activations