© 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. 232719
    Prev
    Next
    INDEX
    Explanations

    multilingual or non-english terms

    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
    anti
    0.51
    ₄
    0.47
     on
    0.47
     Rakh
    0.46
     تحقیق
    0.46
    base
    0.45
    ico
    0.45
     therapists
    0.45
     effective
    0.44
    rental
    0.44
    POSITIVE LOGITS
    趙
    0.48
    შე
    0.47
    郤
    0.46
    文物
    0.46
    <unused48>
    0.45
     размер
    0.45
     инициа
    0.44
    ソン
    0.44
    用紙
    0.44
    ំនួន
    0.44
    Activations Density 0.001%

    No Known Activations