© 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. 233849
    Prev
    Next
    INDEX
    Explanations

    only

    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
    叠
    0.59
    也是
    0.55
    uetooth
    0.45
    普遍
    0.44
    leftharpoons
    0.43
    本身
    0.43
    rtype
    0.43
    活性
    0.43
    }^{*}=\
    0.43
    glyph
    0.43
    POSITIVE LOGITS
    inė
    0.55
    inės
    0.50
     până
    0.47
     multipliers
    0.45
     numai
    0.45
     trebuie
    0.44
     ką
    0.44
    зна
    0.44
     dejar
    0.43
     numeri
    0.43
    Activations Density 0.001%

    No Known Activations