© 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. 77388
    Prev
    Next
    INDEX
    Explanations

    communion, religious services

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

    application processes

    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
     Въ
    0.52
    vorschau
    0.52
     గు
    0.51
     Při
    0.50
    alá
    0.49
     гео
    0.49
     ಹ
    0.48
     থানায়
    0.47
     гульнявыя
    0.47
     начал
    0.47
    POSITIVE LOGITS
     Reese
    0.48
     cruise
    0.47
     Dir
    0.46
     in
    0.45
     Cruise
    0.44
     unanimously
    0.44
     vendor
    0.44
    STAND
    0.44
     C
    0.43
     J
    0.42
    Activations Density 0.000%

    No Known Activations