© 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. 54910
    Prev
    Next
    INDEX
    Explanations

    page numbers and sections

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

    page number identification

    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
    ли
    0.62
    大
    0.52
    0.52
     gráf
    0.52
    ни
    0.51
     zá
    0.51
     tó
    0.51
     proteína
    0.50
    ил
    0.50
    大气
    0.50
    POSITIVE LOGITS
     ಹೃ
    0.48
    OVERRIDES
    0.48
    primir
    0.46
     ಕೂದಲ
    0.46
    continued
    0.44
    asserie
    0.44
     تعیین
    0.43
    ):=
    0.43
     என்றும்
    0.43
    vić
    0.42
    Activations Density 0.006%

    No Known Activations