© 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. 135587
    Prev
    Next
    INDEX
    Explanations

    exclamations

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

    Spanish exclamations and greetings

    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
    ும்
    0.71
    ？
    0.68
    ?..
    0.67
    ला
    0.67
    ين
    0.67
    و
    0.65
    ă
    0.65
    ப்ப
    0.64
    unut
    0.63
    ട
    0.63
    POSITIVE LOGITS
    0
    0.84
    '!
    0.81
    !--
    0.78
    i
    0.77
     !
    0.77
    "!
    0.75
    !",
    0.73
     ！
    0.72
    8
    0.71
     !,
    0.68
    Activations Density 0.109%

    No Known Activations