© 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. 135280
    Prev
    Next
    INDEX
    Explanations

    world, kingdom, unknown, health

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

    file list

    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
     ১৩২২
    0.53
     सिस्टम
    0.52
     нескольких
    0.52
     接
    0.52
     tocó
    0.52
     맞아
    0.50
     августа
    0.50
     acetic
    0.50
     mehreren
    0.50
     moverse
    0.50
    POSITIVE LOGITS
    "
    0.47
    λλά
    0.46
    avik
    0.46
    $
    0.45
    沈
    0.41
    ஞ்ஞான
    0.41
    ong
    0.40
    argaan
    0.40
    曆
    0.39
    í
    0.39
    Activations Density 0.000%

    No Known Activations