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-262K
    4. 923
    Prev
    Next
    INDEX
    Explanations

    shell commands and python code

    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_262k_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
    ↙
    0.74
    破解
    0.68
     blue
    0.66
    鋤
    0.66
    ப்பான
    0.65
     abusive
    0.65
     Abby
    0.64
    ប់
    0.62
     rojo
    0.62
    屢
    0.62
    POSITIVE LOGITS
    Command
    0.59
    Dictionary
    0.58
    command
    0.57
     Dictionary
    0.56
    escap
    0.56
     episodio
    0.55
    віч
    0.55
    flare
    0.54
    atribut
    0.54
    ಗಳ
    0.54
    Activations Density 0.055%

    No Known Activations