© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 44882
    Prev
    Next
    INDEX
    Explanations

    teacherpreneur, thousands, loved, need, fantasy

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

    detective investigation help

    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
     Ambul
    0.42
    总体
    0.41
     सकेगा
    0.41
     Jadi
    0.39
     Current
    0.39
    =(
    0.38
    ↵↵↵↵↵
    0.38
    apeut
    0.38
    ویز
    0.38
    ↵↵↵↵
    0.38
    POSITIVE LOGITS
    河流
    0.50
    ప్పటికీ
    0.42
    ْر
    0.41
    ર
    0.41
    骄
    0.41
    SNS
    0.40
    ниць
    0.40
    мма
    0.40
     récord
    0.40
    नाचा
    0.39
    Activations Density 0.000%

    No Known Activations