© 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. 161294
    Prev
    Next
    INDEX
    Explanations

    European data or forecasts

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

    global variables

    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
     carbs
    0.49
     planks
    0.47
    /[
    0.46
     cereals
    0.44
     expats
    0.44
     fluff
    0.44
     przek
    0.43
     candies
    0.43
     Gost
    0.43
    /
    0.42
    POSITIVE LOGITS
     о
    0.53
    羍
    0.49
     охра
    0.47
     ο
    0.46
     европей
    0.45
    зация
    0.44
     н
    0.44
     астро
    0.44
     बारह
    0.44
     γ
    0.43
    Activations Density 0.000%

    No Known Activations