© 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. 127677
    Prev
    Next
    INDEX
    Explanations

    found in towns

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

    defensive post

    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
     unbe
    0.49
    는
    0.46
     printemps
    0.45
     Neville
    0.45
     hommes
    0.45
    Space
    0.45
     Uncertainty
    0.44
     nacht
    0.44
    是
    0.44
     höchsten
    0.43
    POSITIVE LOGITS
     जाहीर
    0.50
     शिकार
    0.48
     चारों
    0.46
     बहुत
    0.46
     тобто
    0.45
     проник
    0.44
    ukaemia
    0.43
     साझा
    0.43
    นะนำ
    0.43
     ಅಂತ
    0.43
    Activations Density 0.000%

    No Known Activations