© 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. 2948
    Prev
    Next
    INDEX
    Explanations

    Prophet Muhammad, music notation

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

    x, y, and equations

    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
    ക്കിയി
    0.59
    avond
    0.57
    鳕
    0.57
    缜
    0.57
    缛
    0.56
     druż
    0.55
    [multimodal]
    0.55
    ড্রিম
    0.55
    tiket
    0.55
     unapolog
    0.55
    POSITIVE LOGITS
     P
    0.79
    0.77
    ↵
    0.69
     =
    0.68
     )
    0.68
     D
    0.64
     O
    0.64
    ↵↵
    0.63
     p
    0.63
     L
    0.63
    Activations Density 0.002%

    No Known Activations