© 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. 22-GEMMASCOPE-2-RES-16K
    7. 3007
    Prev
    Next
    INDEX
    Explanations

    years 2022 2023

    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_16k_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
    㖅
    0.87
    adolid
    0.86
    跟大家
    0.84
    м
    0.82
     cubierta
    0.81
     Brahmin
    0.75
    yyam
    0.75
     Examiner
    0.74
     সদা
    0.74
    ৭
    0.73
    POSITIVE LOGITS
     می‌
    0.91
     آمده
    0.86
     є
    0.83
     után
    0.82
    崽
    0.82
     Apa
    0.81
     مبلغ
    0.79
    过去了
    0.79
    能
    0.78
    前の
    0.78
    Activations Density 0.042%

    No Known Activations