© 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. 2515
    Prev
    Next
    INDEX
    Explanations

    font and typeface

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

    font, color, bold formatting

    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
    タウン
    0.50
    prestations
    0.49
    pools
    0.49
    INST
    0.48
     anticoagulant
    0.47
    GIT
    0.46
     thrombo
    0.45
    殉
    0.45
    timetable
    0.45
     pharmacokinetic
    0.45
    POSITIVE LOGITS
     font
    0.98
    字体
    0.98
     typeface
    0.96
     Font
    0.92
     fonts
    0.89
     Fonts
    0.88
     шрифт
    0.88
     Verdana
    0.85
     шриф
    0.85
     fontSize
    0.84
    Activations Density 0.026%

    No Known Activations