© 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. 184891
    Prev
    Next
    INDEX
    Explanations

    analytical purposesanalytical

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

    marketing analytics or security operations

    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
     numpy
    0.54
     glitch
    0.52
     potency
    0.51
    ן
    0.50
     oeuvre
    0.49
     voting
    0.49
     dysplasia
    0.49
     inquest
    0.48
     hota
    0.48
    ♻
    0.47
    POSITIVE LOGITS
    രിച്ചി
    0.50
    ਲ
    0.47
    리로
    0.45
    toRadians
    0.43
    owners
    0.42
    ုပ်တို့
    0.42
    owników
    0.41
     Goodbye
    0.41
    ک
    0.41
    igis
    0.40
    Activations Density 0.000%

    No Known Activations