© 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. 12883
    Prev
    Next
    INDEX
    Explanations

    center of interest

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

    centrality and core concepts

    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
    ق
    0.85
    ור
    0.83
    ল
    0.83
    هم
    0.82
    ק
    0.79
     as
    0.72
    ל
    0.71
    ص
    0.68
    ا
    0.66
    ని
    0.66
    POSITIVE LOGITS
     центр
    1.32
     中心
    1.20
    central
    1.19
     центра
    1.19
     centrale
    1.17
    Center
    1.16
     CENTER
    1.16
    中心
    1.15
     centro
    1.14
     centre
    1.13
    Activations Density 0.094%

    No Known Activations