© 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. 19603
    Prev
    Next
    INDEX
    Explanations

    dates, times, and publications

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

    contacting and explaining

    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
     ALSO
    0.40
    தியான
    0.39
    嗟
    0.39
    bigger
    0.37
    लावा
    0.36
     bigger
    0.36
    振兴
    0.36
    ходить
    0.36
     Coins
    0.35
     Imagination
    0.35
    POSITIVE LOGITS
     recibieron
    0.42
    gdock
    0.39
     veľmi
    0.38
    ={(
    0.37
    raron
    0.36
    рованной
    0.36
    ították
    0.36
     noirâtres
    0.36
    পন্ন
    0.36
     tetra
    0.36
    Activations Density 0.000%

    No Known Activations