© 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. 228849
    Prev
    Next
    INDEX
    Explanations

    VIP amenities

    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
     edge
    0.48
    小学
    0.48
     edged
    0.48
     sớm
    0.47
    2
    0.46
     pojawi
    0.46
    itty
    0.46
     updates
    0.45
     paths
    0.45
     spanned
    0.45
    POSITIVE LOGITS
    vasena
    0.57
    enzione
    0.48
     cest
    0.47
     Nizam
    0.47
    なさ
    0.47
     cet
    0.46
     Mato
    0.46
    勖
    0.45
    ি
    0.45
    처리
    0.45
    Activations Density 0.000%

    No Known Activations