© 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. 208657
    Prev
    Next
    INDEX
    Explanations

    binary relations, periodic analysis, abdication

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

    this is followed by a description

    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
     Olive
    0.48
     Côte
    0.46
     Aloe
    0.45
     a
    0.45
    ↵
    0.45
     weathered
    0.45
     própri
    0.44
     அப்படி
    0.44
     Jay
    0.43
     olive
    0.42
    POSITIVE LOGITS
    akn
    0.50
    푚
    0.45
    igenschaften
    0.44
    均匀
    0.44
     benutzer
    0.44
    ৬০
    0.44
     skr
    0.43
     veck
    0.43
     bimodule
    0.42
    ৬৫
    0.42
    Activations Density 0.000%

    No Known Activations