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. 22-GEMMASCOPE-2-RES-65K
    4. 3424
    Prev
    Next
    INDEX
    Explanations

    suffixes like ology and ari

    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_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
     antagonistic
    0.80
    shortcut
    0.76
    ずれ
    0.74
    িনীত
    0.74
    inputenc
    0.74
     числен
    0.72
    chomp
    0.71
    渙
    0.71
    laptop
    0.71
     conclusively
    0.69
    POSITIVE LOGITS
    (?)
    0.94
    -
    0.89
    -}$
    0.88
     negra
    0.83
    ⌬
    0.77
    Prototype
    0.73
     Direito
    0.73
    ಗೊಂಡ
    0.72
     Maori
    0.71
     extraordinaire
    0.70
    Activations Density 0.409%

    No Known Activations