© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 66846
    Prev
    Next
    INDEX
    Explanations

    dates and lists

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

    exploring such, opposite order, constant ratio

    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
    计
    0.53
    是你
    0.48
    IDADES
    0.45
    ikat
    0.45
    ించండి
    0.45
     வேக
    0.44
    ığını
    0.44
    当你
    0.44
    метр
    0.43
     bö
    0.43
    POSITIVE LOGITS
    もので
    0.49
    ould
    0.46
     захворю
    0.45
     ቤ
    0.45
    ส
    0.44
    currentPage
    0.44
     ||
    0.43
     Inher
    0.42
    ਉ
    0.42
    Casual
    0.42
    Activations Density 0.003%

    No Known Activations