© 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. 143453
    Prev
    Next
    INDEX
    Explanations

    looking for or buying

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

    potential issues and complexity

    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
    uisce
    0.48
    coloring
    0.46
    性を
    0.46
    孜
    0.46
    モリ
    0.46
    escens
    0.46
     سلي
    0.46
    性は
    0.45
    әй
    0.45
    虽
    0.45
    POSITIVE LOGITS
     komplet
    0.59
     iron
    0.52
     estima
    0.52
     esk
    0.50
     imshow
    0.50
     kontroller
    0.50
    .
    0.49
     acceptor
    0.48
     mashed
    0.47
     hars
    0.46
    Activations Density 0.002%

    No Known Activations