© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 6488
    Prev
    Next
    INDEX
    Explanations

    automatic subscription

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    ائص
    0.58
    <unused973>
    0.56
    َب
    0.55
    Historically
    0.55
     quelquefois
    0.54
    َد
    0.53
    <unused311>
    0.53
    <unused683>
    0.53
     nonzero
    0.52
    VIDENCE
    0.52
    POSITIVE LOGITS
    ≙
    0.73
     Wochen
    0.73
     Sozial
    0.71
     Medien
    0.70
    ´
    0.70
     Groß
    0.69
     Entwicklung
    0.69
     WLAN
    0.69
     „
    0.69
     Finanz
    0.69
    Activations Density 0.007%

    No Known Activations