© 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. 199683
    Prev
    Next
    INDEX
    Explanations

    writing name and image

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

    requires more

    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
     пра
    0.45
    ра
    0.43
     ф
    0.43
     фор
    0.42
    ચા
    0.42
     кле
    0.42
    кле
    0.42
     ран
    0.41
     ≥
    0.41
     occident
    0.41
    POSITIVE LOGITS
    der
    0.52
    tops
    0.51
    steel
    0.50
    er
    0.49
    m
    0.48
    o
    0.48
    testing
    0.48
    ekin
    0.48
    in
    0.47
    editor
    0.47
    Activations Density 0.001%

    No Known Activations