© 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. 172966
    Prev
    Next
    INDEX
    Explanations

    mount engineer badge daily cart

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

    people who

    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
    செல்
    0.48
    ubicin
    0.47
    機の
    0.47
    哲
    0.46
    裝
    0.45
     Проци
    0.45
    儕
    0.45
     県
    0.44
    績
    0.44
     よる
    0.44
    POSITIVE LOGITS
    ge
    0.56
    em
    0.52
    te
    0.49
    ep
    0.48
    waard
    0.48
    ew
    0.47
    aja
    0.47
    实际
    0.45
    ed
    0.45
    tour
    0.44
    Activations Density 0.001%

    No Known Activations