© 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. 124753
    Prev
    Next
    INDEX
    Explanations

    specific titles and descriptions

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

    numbers, dates, or sequences

    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
     सम्मेलन
    0.55
     条
    0.53
     電
    0.52
     電力
    0.52
     Park
    0.48
    Config
    0.48
    Enable
    0.47
    Layout
    0.46
    Park
    0.46
     మహిళ
    0.46
    POSITIVE LOGITS
     officielles
    0.56
    реи
    0.52
    ᠴ
    0.52
     atos
    0.51
    ти
    0.51
     excer
    0.51
    си
    0.49
    вара
    0.49
     konkuren
    0.49
     doce
    0.48
    Activations Density 0.000%

    No Known Activations