© 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. 51829
    Prev
    Next
    INDEX
    Explanations

    ever been

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

    punctuation and common words

    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
    лед
    0.46
     ಸಾವಿರ
    0.45
    າມາດ
    0.43
     exemplified
    0.42
     ог
    0.42
     이후
    0.42
     accesible
    0.41
    𝓪
    0.41
    Corollary
    0.40
    хих
    0.40
    POSITIVE LOGITS
     Díaz
    0.49
     পুনঃ
    0.47
     Pilates
    0.47
     Waist
    0.46
     Diaz
    0.45
     Command
    0.45
     ([
    0.45
     Nautical
    0.44
     Williamson
    0.44
     Davis
    0.43
    Activations Density 0.000%

    No Known Activations