© 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. 116060
    Prev
    Next
    INDEX
    Explanations

    presents arguments, evaluations, and activity

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

    words in multiple languages

    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
     I
    0.58
    ー
    0.51
     C
    0.49
    もちろん
    0.49
     original
    0.48
     as
    0.47
    ’
    0.47
     ursprüng
    0.46
    0.46
     agen
    0.46
    POSITIVE LOGITS
     బ్రిటి
    0.50
    ంగళ
    0.48
    క్కడ
    0.46
    蛞
    0.45
    导体
    0.45
     BLUENRG
    0.45
     इसीलिए
    0.45
    ésie
    0.44
    ెండు
    0.43
     బ్రి
    0.43
    Activations Density 0.000%

    No Known Activations