© 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. 48704
    Prev
    Next
    INDEX
    Explanations

    after afternoon of a faun

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

    list items and descriptions

    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
    ారులు
    0.49
    Otro
    0.48
    𝟎
    0.45
    एमपी
    0.44
    лото
    0.44
     MINISTRY
    0.44
    neys
    0.44
    pares
    0.44
    Wishing
    0.44
    While
    0.43
    POSITIVE LOGITS
    權
    0.47
     ストレ
    0.46
    ွန်
    0.46
     recombination
    0.46
     homogé
    0.46
     richten
    0.44
    ogeneous
    0.44
    วัสดี
    0.43
     контро
    0.43
     cohomology
    0.43
    Activations Density 0.000%

    No Known Activations