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. 1033
    Prev
    Next
    INDEX
    Explanations

    localhost and IP addresses

    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
     रोजी
    0.78
     Contrary
    0.65
     둘
    0.65
    둘
    0.63
     ചില
    0.62
     ಕೆಲ
    0.62
     فيه
    0.61
    ដែរ
    0.60
     sling
    0.60
     Mano
    0.60
    POSITIVE LOGITS
    tailwindcss
    0.61
    profen
    0.60
    nment
    0.59
    妒
    0.58
    arnos
    0.58
    ower
    0.58
    💒
    0.58
    开发者
    0.57
    炆
    0.57
    example
    0.57
    Activations Density 0.008%

    No Known Activations