© 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. 104066
    Prev
    Next
    INDEX
    Explanations

    Added content confirmation

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

    technical concepts or measurement

    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
     Cavs
    0.47
    ডেম
    0.45
    手
    0.45
     Convergence
    0.44
    $.
    0.44
     előtt
    0.44
    เพื่อน
    0.44
     பார்ப்ப
    0.43
     IncludeField
    0.43
    庀
    0.43
    POSITIVE LOGITS
     salinity
    0.54
     repressed
    0.49
     metall
    0.49
     transmitted
    0.46
     ধাত
    0.45
    制御
    0.45
     ceased
    0.43
     unsus
    0.42
     공급
    0.42
     sucrose
    0.42
    Activations Density 0.001%

    No Known Activations