© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 9541
    Prev
    Next
    INDEX
    Explanations

    deep learning and machine learning

    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
     Committees
    1.47
     En
    1.36
     versch
    1.35
    of
    1.30
     Bí
    1.29
     O
    1.29
     nie
    1.26
     Advisory
    1.24
    と思います
    1.23
     purse
    1.19
    POSITIVE LOGITS
    ها
    1.78
    theless
    1.59
    trone
    1.57
    iempo
    1.54
    ла
    1.53
    इयों
    1.49
    σαν
    1.42
    FA
    1.42
    մ
    1.41
    tahun
    1.38
    Activations Density 0.075%

    No Known Activations