© 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. 12181
    Prev
    Next
    INDEX
    Explanations

    computation, protocol, learning, Stewart

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

    Static, dataset, technical

    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
     वैलेंटाइन
    0.51
     ನಿಮ್ಮ
    0.48
     మే
    0.48
     ஒவ்வ
    0.47
     ආරක්ෂ
    0.47
     rekom
    0.47
     Tatha
    0.46
    霭
    0.46
     एमजी
    0.46
     মঙ্গল
    0.46
    POSITIVE LOGITS
    上
    0.47
     conc
    0.45
    0.44
    ал
    0.42
    protocol
    0.41
    Computation
    0.39
    <0xE2>
    0.38
    <0x80>
    0.37
     calorimeter
    0.37
    flavor
    0.36
    Activations Density 0.001%

    No Known Activations