© 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. 57321
    Prev
    Next
    INDEX
    Explanations

    preferences, options, settings

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

    file properties

    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
    读者
    0.49
    如下
    0.48
    在
    0.48
     trouver
    0.47
     zeroes
    0.46
     succès
    0.46
    路由器
    0.46
     صارف
    0.46
     nghề
    0.46
     ríos
    0.45
    POSITIVE LOGITS
    ?
    0.51
    చన
    0.46
    BMI
    0.45
    Britain
    0.45
    RANK
    0.45
     Брита
    0.44
    tm
    0.44
    Trains
    0.44
    ground
    0.43
    tions
    0.43
    Activations Density 0.000%

    No Known Activations