© 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. 14916
    Prev
    Next
    INDEX
    Explanations

    about every

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

    The Strip EU History

    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
    ield
    0.43
     człowieka
    0.42
     ilişk
    0.42
     pamię
    0.42
    ẏ
    0.42
     стране
    0.42
     obsług
    0.41
    寥
    0.41
     Поль
    0.41
     {[
    0.41
    POSITIVE LOGITS
    DUP
    0.53
    媳
    0.48
    شد
    0.47
    pro
    0.46
    Teller
    0.46
    شوند
    0.45
     gestational
    0.45
    apayati
    0.45
    하시는
    0.45
     centri
    0.44
    Activations Density 0.000%

    No Known Activations