© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 4011
    Prev
    Next
    INDEX
    Explanations

    Tujuan Finansial

    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
     소프트
    0.93
     Vermont
    0.90
    意大利
    0.88
     fantastical
    0.84
    听
    0.82
     SYSTEMS
    0.81
    鸽
    0.81
    É
    0.81
    墨西哥
    0.80
     OR
    0.80
    POSITIVE LOGITS
     sudah
    2.37
     sesuai
    2.28
     hanya
    2.20
     tidak
    2.20
     sehingga
    2.18
     dapat
    2.16
     tahun
    2.16
     jika
    2.13
     seperti
    2.11
     dengan
    2.10
    Activations Density 0.011%

    No Known Activations