© 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. 246428
    Prev
    Next
    INDEX
    Explanations

    numbers or simple words

    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
    ي
    0.57
    ǎ
    0.46
    ಾಂಶ
    0.45
    يلا
    0.45
     snuff
    0.45
    mq
    0.45
     imported
    0.44
    ì
    0.44
    י
    0.43
    ">
    0.42
    POSITIVE LOGITS
    ifient
    0.46
    硃
    0.46
    ITING
    0.46
     लंबित
    0.45
    plitude
    0.45
    Ꮙ
    0.44
     તૈયાર
    0.44
    ваний
    0.44
     номера
    0.43
    ocomplete
    0.43
    Activations Density 0.002%

    No Known Activations