© 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. 165719
    Prev
    Next
    INDEX
    Explanations

    goal, result, race

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

    packaging, becoming, cost, action, match

    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
     {}",
    0.46
     然而
    0.46
     ancak
    0.46
     archaeological
    0.45
     fijn
    0.45
    ัม
    0.44
     bunun
    0.44
     cheerio
    0.44
     ఆహ
    0.44
     amply
    0.43
    POSITIVE LOGITS
    缟
    0.49
     Bestand
    0.48
    étés
    0.46
     İş
    0.45
    尔多
    0.45
     Conception
    0.45
    لک
    0.44
    ieke
    0.44
     Рі
    0.44
    Motion
    0.44
    Activations Density 0.001%

    No Known Activations