© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14923
    Prev
    Next
    INDEX
    Explanations

    Perl code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ños
    0.78
    емости
    0.77
    NonUser
    0.76
    pha
    0.76
    迤
    0.75
     Rockies
    0.72
     í
    0.71
     Endurance
    0.71
     Marques
    0.71
     yǐ
    0.70
    POSITIVE LOGITS
     Perl
    1.09
    perl
    0.97
     perl
    0.95
     qw
    0.91
    undef
    0.84
    $^
    0.79
     wyra
    0.78
    DESTROY
    0.78
    qw
    0.76
     ($_
    0.75
    Activations Density 0.032%

    No Known Activations