© 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. 71847
    Prev
    Next
    INDEX
    Explanations

    listing examples within a category

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

    lists items or examples

    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
     are
    0.59
    you
    0.58
    都
    0.57
     be
    0.56
    that
    0.54
    på
    0.54
    ↵↵
    0.53
    ash
    0.52
    begin
    0.52
    this
    0.51
    POSITIVE LOGITS
    ל
    0.95
    л
    0.89
    ल
    0.78
    ل
    0.74
     consistente
    0.69
    ли
    0.68
     bisogno
    0.66
    т
    0.66
     fueled
    0.65
    ר
    0.64
    Activations Density 0.057%

    No Known Activations