© 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. 27822
    Prev
    Next
    INDEX
    Explanations

    before someone's eyes

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

    descriptive definitions, explanations

    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
     دارای
    0.50
    佩
    0.48
    鹧
    0.45
    ැ
    0.45
     ক্ষতির
    0.45
     modification
    0.45
     स्वर
    0.44
    权利
    0.42
     Ngày
    0.42
     Deduction
    0.42
    POSITIVE LOGITS
    `(
    0.52
     különb
    0.51
    그리고
    0.50
    ikopter
    0.50
     dring
    0.49
    cc
    0.48
    rig
    0.48
    its
    0.48
    }(
    0.48
    ng
    0.46
    Activations Density 0.001%

    No Known Activations