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. 17-GEMMASCOPE-2-RES-65K
    4. 1937
    Prev
    Next
    INDEX
    Explanations

    website links and common phrases

    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_17_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
    creas
    0.84
     theorem
    0.84
    atched
    0.83
    isimple
    0.83
    oq
    0.79
    定理
    0.79
    疃
    0.79
    띈
    0.78
    oustic
    0.78
    igten
    0.78
    POSITIVE LOGITS
    Ī
    1.22
    Ĭ
    1.03
    Ģ
    1.01
     However
    0.94
    Ĥ
    0.93
    Į
    0.93
     This
    0.93
     Copyright
    0.92
     |,
    0.92
    ī
    0.92
    Activations Density 0.001%

    No Known Activations