© 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. 143344
    Prev
    Next
    INDEX
    Explanations

    caution the public

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

    directives and designations

    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
    मिस्ट्री
    0.48
     '.')
    0.46
    话
    0.45
     Store
    0.44
    愭
    0.44
    ੈਂ
    0.44
    인데요
    0.43
    욤
    0.43
     엄청
    0.42
     ขอ
    0.42
    POSITIVE LOGITS
     evolving
    0.54
    ها
    0.49
     alianza
    0.49
    ll
    0.46
     acción
    0.45
    idal
    0.45
     antigu
    0.44
    ंगिक
    0.44
     anz
    0.44
    mpl
    0.43
    Activations Density 0.000%

    No Known Activations