© 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. 22-GEMMASCOPE-2-RES-262K
    4. 873
    Prev
    Next
    INDEX
    Explanations

    I will take sick leave

    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
    י
    1.29
     radiology
    1.20
    یه
    1.20
    gboost
    1.18
    Phys
    1.15
     woodlands
    1.12
    ITOR
    1.09
     Kimura
    1.09
    yap
    1.08
     Batteries
    1.08
    POSITIVE LOGITS
    முடி
    0.97
    वाड़ा
    0.83
     educated
    0.82
    ুগত্য
    0.82
     occasional
    0.82
    }-$
    0.81
     महेंद्र
    0.81
    信用卡
    0.81
    ود
    0.81
     erupted
    0.80
    Activations Density 0.002%

    No Known Activations