© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10942
    Prev
    Next
    INDEX
    Explanations

    enable or disable

    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_9_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
     not
    1.06
     be
    0.94
    姆斯
    0.93
    ម្បី
    0.92
     এজন্য
    0.92
     lik
    0.90
    빌
    0.89
    Not
    0.88
    тельства
    0.87
     чем
    0.86
    POSITIVE LOGITS
    rijke
    1.35
     crosstalk
    1.22
    趵
    1.21
    ுக்கு
    1.20
    iving
    1.19
     legalization
    1.19
    नियों
    1.18
    athed
    1.16
    ंजलि
    1.16
    ীদ
    1.15
    Activations Density 0.000%

    No Known Activations