© 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. 25853
    Prev
    Next
    INDEX
    Explanations

    emojis, reactions, and emotions

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

    positive emojis and expressions

    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
     হয়ত
    0.46
    垁
    0.44
    㸮
    0.42
    矨
    0.42
     கரை
    0.41
    떄
    0.41
     인해
    0.39
    м
    0.39
    気の
    0.39
    䉍
    0.39
    POSITIVE LOGITS
    a
    0.63
    on
    0.59
    :
    0.53
    s
    0.50
    that
    0.47
    e
    0.46
    🙏🙏
    0.46
    H
    0.45
    T
    0.45
    diamond
    0.45
    Activations Density 0.002%

    No Known Activations