© 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. 124860
    Prev
    Next
    INDEX
    Explanations

    recent powered audio future exchange

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

    tours available

    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
     પ્રય
    0.45
     schedule
    0.42
     vá
    0.42
    ↵
    0.42
     butterfly
    0.42
     fluctuation
    0.41
     disk
    0.40
    Ch
    0.40
     creepy
    0.40
     Brack
    0.40
    POSITIVE LOGITS
    ಫ
    0.56
     bhavanti
    0.54
    ieli
    0.52
    יה
    0.49
     imasmim
    0.49
    等は
    0.49
     interstitiis
    0.48
    लोग
    0.48
    ട്ടില്‍
    0.48
    inians
    0.48
    Activations Density 0.000%

    No Known Activations