© 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. 33881
    Prev
    Next
    INDEX
    Explanations

    crisp

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

    crispness and "Text Line"

    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
    闪
    0.51
    ;;)
    0.50
    ەتی
    0.47
     반지
    0.47
    둘
    0.45
     homologs
    0.45
     dull
    0.45
    を描
    0.44
     चमक
    0.43
    ｦ
    0.43
    POSITIVE LOGITS
    cris
    0.86
     crisp
    0.81
     Cris
    0.80
     cris
    0.79
    Cris
    0.75
     Crisp
    0.75
     crispy
    0.73
     crunchy
    0.66
     CRIS
    0.63
    crunch
    0.58
    Activations Density 0.015%

    No Known Activations