© 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. 90014
    Prev
    Next
    INDEX
    Explanations

    professions, events, sponsors

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

    explaining scope and focus

    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
    紹介
    0.46
     transducers
    0.46
    ন
    0.44
     caoutchouc
    0.44
     nhất
    0.43
     candidature
    0.43
    \
    0.43
     название
    0.43
    ịnh
    0.43
    }-\
    0.42
    POSITIVE LOGITS
     أنا
    0.52
     નિર્ણ
    0.44
     قام
    0.43
     kaldı
    0.43
     Sprou
    0.42
     कार्र
    0.42
     Diane
    0.41
     Stacy
    0.41
     قانونی
    0.41
     मूड
    0.40
    Activations Density 0.000%

    No Known Activations