© 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. 12316
    Prev
    Next
    INDEX
    Explanations

    names and foreign words

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

    Lubenian

    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
     loosing
    0.47
     (~
    0.43
    Notice
    0.42
     Beside
    0.42
    ـ
    0.42
    🔍
    0.40
    edy
    0.39
    And
    0.39
    Hight
    0.39
     (>
    0.38
    POSITIVE LOGITS
     magní
    0.44
     Pursuant
    0.44
     великолеп
    0.44
    🪐
    0.42
     коронави
    0.41
     ஏராளமான
    0.41
     subpar
    0.41
    மஹ
    0.40
     esche
    0.40
    !!!!!!!!!!!!!!!!
    0.40
    Activations Density 0.145%

    No Known Activations