© 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. 195861
    Prev
    Next
    INDEX
    Explanations

    exclamations!

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

    emphasis and factual statements

    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
    0.83
    ﺮ
    0.81
    ING
    0.78
    ни
    0.78
    of
    0.78
    не
    0.75
    ک
    0.73
    Б
    0.72
    ně
    0.72
    эн
    0.72
    POSITIVE LOGITS
     adju
    0.89
     hypothes
    0.82
    i
    0.77
     adjuvant
    0.73
     bevel
    0.67
     intrinsic
    0.66
     unravel
    0.65
     risks
    0.64
     acted
    0.64
     adapts
    0.64
    Activations Density 0.157%

    No Known Activations