© 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. 19758
    Prev
    Next
    INDEX
    Explanations

    exclamation points and names

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

    highly recommend with exclamations

    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
    এছাড়া
    0.45
    ಂತ್ರಿ
    0.44
    そのため
    0.41
    加えて
    0.39
    간
    0.39
     अंध
    0.39
     దూర
    0.39
    धीरे
    0.38
     մաս
    0.38
     निराशा
    0.38
    POSITIVE LOGITS
     sf
    0.46
     !!!!!
    0.45
     Jamie
    0.45
     来自
    0.44
     fs
    0.44
     ä
    0.43
     Mike
    0.42
     Harriet
    0.42
     Aaron
    0.42
     pictured
    0.42
    Activations Density 0.009%

    No Known Activations