© 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. 146020
    Prev
    Next
    INDEX
    Explanations

    judgment, attach, LED, flower, factory

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

    design project completion

    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
    谋
    0.48
    忘了
    0.47
    靠近
    0.46
    ла
    0.46
    胶
    0.46
    害者
    0.45
    肠
    0.45
    自身的
    0.45
    ताल
    0.43
    තාව
    0.43
    POSITIVE LOGITS
     NodeRef
    0.48
    ocks
    0.48
     ech
    0.48
     Eno
    0.46
     Orc
    0.44
     höch
    0.44
    オーク
    0.44
    ل
    0.42
     predicted
    0.42
    ሮች
    0.42
    Activations Density 0.002%

    No Known Activations