© 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. 56945
    Prev
    Next
    INDEX
    Explanations

    activities/*

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

    foreign words and phrases

    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
    IN
    0.57
     a
    0.50
    った
    0.50
    F
    0.49
    alir
    0.48
    RE
    0.48
    <strong>
    0.47
    太
    0.47
    network
    0.46
    ocere
    0.45
    POSITIVE LOGITS
     preparação
    0.46
     سوری
    0.46
    Decedent
    0.45
     শাস্ত্র
    0.45
     موز
    0.45
     شئ
    0.44
     মূর্তি
    0.44
     处理
    0.44
    vDash
    0.43
     случай
    0.43
    Activations Density 0.000%

    No Known Activations