© 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. 29-GEMMASCOPE-2-RES-65K
    4. 5021
    Prev
    Next
    INDEX
    Explanations

    Carl and psychology concepts

    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_29_width_65k_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
     
    0.80
     the
    0.72
    การ
    0.69
    ↵
    0.60
     "
    0.57
     “
    0.56
     New
    0.54
    リ
    0.54
    లో
    0.53
    ↵↵
    0.53
    POSITIVE LOGITS
    pośred
    0.71
    状态
    0.68
    价格
    0.64
    ция
    0.62
    <unused1745>
    0.61
     namani
    0.60
    消息
    0.60
    ınıza
    0.60
     Fleurit
    0.60
    空间
    0.59
    Activations Density 0.000%

    No Known Activations