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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 1435
    Prev
    Next
    INDEX
    Explanations

    Cat categories (Cat5e, Cat6a)

    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
     disbelief
    0.52
    ങ്ങളുടെ
    0.52
     contemplation
    0.52
     √(
    0.49
     maggior
    0.49
     millennials
    0.49
     pats
    0.49
     amore
    0.48
    ateľ
    0.48
    hetra
    0.48
    POSITIVE LOGITS
    0
    0.97
    B
    0.95
    ″]
    0.84
    系列
    0.79
    x
    0.79
    5
    0.76
    ″
    0.76
    b
    0.74
    X
    0.74
    ′,
    0.73
    Activations Density 0.503%

    No Known Activations