© 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. 220050
    Prev
    Next
    INDEX
    Explanations

    New York Times

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

    arguments and counterarguments

    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
    '
    0.51
    見
    0.46
    iling
    0.46
     Games
    0.45
     Governor
    0.42
    魔
    0.42
    輝
    0.41
    積み
    0.41
    lower
    0.41
     Would
    0.41
    POSITIVE LOGITS
     intensidad
    0.50
     ఆగ
    0.48
     этапе
    0.46
    镗
    0.45
     مشینوں
    0.45
    inink
    0.45
     напряжения
    0.45
     문제는
    0.44
     ۱۰
    0.44
     చేసిన
    0.44
    Activations Density 0.000%

    No Known Activations