© 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. 1318
    Prev
    Next
    INDEX
    Explanations

    loudly expressing action

    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
    defin
    0.45
     معظم
    0.42
     Longitudinal
    0.40
    ថ្
    0.39
    __).
    0.39
     इंटेलिज
    0.38
     intelligence
    0.38
     खुफिया
    0.38
    ༠
    0.38
     epistem
    0.38
    POSITIVE LOGITS
    🍼
    0.47
    board
    0.43
    ة
    0.43
    డో
    0.42
     rebus
    0.42
     Nope
    0.41
    Wait
    0.40
     baby
    0.40
    姆
    0.40
     işte
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.