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. 41095
    Prev
    Next
    INDEX
    Explanations

    I/O operations

    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
    corr
    0.74
    cuisine
    0.74
    demo
    0.72
    жима
    0.72
    Izq
    0.69
    genre
    0.69
    infix
    0.69
    煐
    0.68
    Down
    0.67
    ാര്‍
    0.67
    POSITIVE LOGITS
     O
    0.91
     II
    0.88
    O
    0.87
     IO
    0.86
     Operation
    0.86
     III
    0.81
    पुट
    0.78
    Operation
    0.75
     glLight
    0.75
     syscall
    0.73
    Activations Density 0.010%

    No Known Activations