© 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. 248631
    Prev
    Next
    INDEX
    Explanations

    licenses granted

    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
    вих
    0.49
    OHN
    0.46
    カイブ
    0.46
    न
    0.46
    л
    0.46
    pena
    0.45
    n
    0.45
     desarroll
    0.44
    PLE
    0.43
    scroll
    0.42
    POSITIVE LOGITS
     alcuna
    0.50
    felter
    0.49
     spying
    0.48
     Hermione
    0.48
     Giulia
    0.46
     هیچ
    0.46
     결혼
    0.46
     प्ला
    0.46
     🎉
    0.46
     Chloe
    0.45
    Activations Density 0.001%

    No Known Activations