© 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. 235905
    Prev
    Next
    INDEX
    Explanations

    wept, draws, excels, versed

    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
    ској
    0.48
     mangiare
    0.47
     alimentação
    0.47
    وجوان
    0.46
    ціа
    0.45
    ﻟ
    0.44
    Farm
    0.44
    إذا
    0.43
    仡
    0.43
    생활
    0.43
    POSITIVE LOGITS
     入っ
    0.50
     書い
    0.49
     トート
    0.46
     แน
    0.45
    អេឡិចត្រូនិច
    0.43
     quieren
    0.43
     ран
    0.42
     stren
    0.42
     証明
    0.42
    ritte
    0.42
    Activations Density 0.000%

    No Known Activations