© 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. 245096
    Prev
    Next
    INDEX
    Explanations

    foreign language characters and 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
    бом
    0.52
    aña
    0.50
    κε
    0.50
    ме
    0.49
    كا
    0.49
    곰
    0.49
     twig
    0.49
     otoño
    0.49
    값을
    0.48
    три
    0.48
    POSITIVE LOGITS
    ها
    0.56
    able
    0.52
    事件
    0.45
    人
    0.44
    do
    0.44
    ul
    0.42
    ary
    0.41
    器官
    0.40
    入
    0.40
    riminal
    0.39
    Activations Density 0.000%

    No Known Activations