© 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. 130919
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, or specific characters

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

    "just" or "be"

    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
     მდ
    0.52
    aktur
    0.50
     goc
    0.49
    牛奶
    0.47
     mlijeka
    0.46
     i
    0.45
     certe
    0.45
     العين
    0.45
     Ini
    0.44
     aluminium
    0.44
    POSITIVE LOGITS
    6
    0.56
    8
    0.54
     discourses
    0.45
    5
    0.45
    月
    0.44
    9
    0.43
     armies
    0.43
    ง
    0.43
    雅
    0.43
    ிட்ட
    0.42
    Activations Density 0.000%

    No Known Activations