© 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. 15446
    Prev
    Next
    INDEX
    Explanations

    named entities or technical components

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

    keywords followed by definitions/code

    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
    শালী
    0.47
    astudio
    0.40
    াতাড়ি
    0.40
    moil
    0.40
    মূলক
    0.40
    ulis
    0.39
     a
    0.39
    ulk
    0.38
    দিনের
    0.38
    पणा
    0.38
    POSITIVE LOGITS
    、
    0.62
    ،
    0.57
    ，
    0.57
     counterpart
    0.50
     symbi
    0.46
    ,
    0.45
    ၊
    0.45
     egen
    0.44
    、「
    0.44
     branche
    0.41
    Activations Density 0.067%

    No Known Activations