© 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. 238805
    Prev
    Next
    INDEX
    Explanations

    metric analog, realtime coverage, ensure guarantee

    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
    ısından
    0.47
    etak
    0.46
    nto
    0.45
    selecting
    0.44
    ྕ
    0.44
    lée
    0.44
    stered
    0.44
    匆
    0.43
    rps
    0.43
    kz
    0.43
    POSITIVE LOGITS
     aren
    0.48
     government
    0.45
     прави
    0.44
     governo
    0.44
     properly
    0.43
     Professor
    0.43
     heterozyg
    0.42
     satis
    0.42
     compatibility
    0.42
     hae
    0.42
    Activations Density 0.000%

    No Known Activations