© 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. 163511
    Prev
    Next
    INDEX
    Explanations

    for prayer, costs, disposal

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

    more aid

    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
    $(\
    0.48
    wab
    0.46
     предупре
    0.45
     повторя
    0.45
     демокра
    0.45
    ﾜ
    0.45
     दक्षता
    0.44
    Референ
    0.44
    蓽
    0.44
    ához
    0.44
    POSITIVE LOGITS
     Nico
    0.49
     Elaine
    0.46
     Zell
    0.46
     Alec
    0.46
    兒
    0.46
     Conner
    0.46
     Zaw
    0.45
     Alexandria
    0.45
     mesenteric
    0.44
     Tengah
    0.44
    Activations Density 0.000%

    No Known Activations