© 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. 34804
    Prev
    Next
    INDEX
    Explanations

    Paul praying

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

    specific descriptions or details

    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
    Tecla
    0.50
    ‌آ
    0.47
     procede
    0.47
    ENSOR
    0.45
    嫒
    0.45
     algorit
    0.44
    慜
    0.44
    Durante
    0.43
    Productos
    0.43
    Cookie
    0.43
    POSITIVE LOGITS
     boarded
    0.49
     fier
    0.47
    ò
    0.46
     ll
    0.44
     près
    0.43
     çat
    0.43
     painted
    0.42
     dott
    0.42
     splashed
    0.42
    δά
    0.41
    Activations Density 0.000%

    No Known Activations