Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 6157
    Prev
    Next
    INDEX
    Explanations

    list of

    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
    cvtColor
    1.01
     grantResults
    0.91
    嶺
    0.86
     cooled
    0.83
    ি
    0.81
    দি
    0.81
    庁
    0.81
    يتر
    0.81
    י
    0.81
    দী
    0.80
    POSITIVE LOGITS
    icle
    1.64
     comprehension
    1.53
     Compre
    1.40
    owel
    1.37
    ENING
    1.35
    icles
    1.34
     comprehens
    1.31
     items
    1.29
    ENER
    1.29
    serv
    1.28
    Activations Density 0.094%

    No Known Activations