© 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. 4783
    Prev
    Next
    INDEX
    Explanations

    phone numbers and dates

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

    https links

    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
     ২০১০
    0.35
    文档
    0.33
     Nguyễn
    0.32
     родился
    0.32
    Tìm
    0.31
     định
    0.30
     Số
    0.30
    ４
    0.30
    轴
    0.30
     huyện
    0.30
    POSITIVE LOGITS
     stessa
    0.40
     كذلك
    0.34
     hacerlo
    0.33
     stessi
    0.33
     stesso
    0.32
     pripad
    0.32
     sepen
    0.31
     grosse
    0.30
     irres
    0.30
     correspondingly
    0.30
    Activations Density 0.031%

    No Known Activations