© 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. 8852
    Prev
    Next
    INDEX
    Explanations

    places and names

    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
     बिन
    0.62
     TextBox
    0.54
    pecia
    0.52
     concise
    0.52
     黒
    0.52
     diphtheria
    0.52
     フラワー
    0.52
    Ყ
    0.51
     ลักษณะ
    0.50
     Lich
    0.50
    POSITIVE LOGITS
    生产
    0.44
    ’
    0.44
    REAT
    0.41
    埸
    0.41
    电
    0.40
    ູ
    0.40
    ర్
    0.40
    存在
    0.40
    στ
    0.40
    ENVIRONMENT
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.