© 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. 38023
    Prev
    Next
    INDEX
    Explanations

    state setters like setCurrent, setSelected, setData

    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
    }.
    0.44
    :
    0.43
     yine
    0.42
     luận
    0.39
     likewise
    0.39
    <li>
    0.39
    などが
    0.38
    ер
    0.38
    });
    0.38
    РА
    0.38
    POSITIVE LOGITS
    inox
    0.42
    óra
    0.41
     रिश्
    0.40
    getActivity
    0.40
    JScripts
    0.39
    webservices
    0.39
    uttaa
    0.39
    chanical
    0.38
    giène
    0.38
    oriya
    0.38
    Activations Density 0.000%

    No Known Activations