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. 22-GEMMASCOPE-2-RES-65K
    4. 4064
    Prev
    Next
    INDEX
    Explanations

    course introductions

    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
    hes
    0.91
    ƒ
    0.89
     coul
    0.89
    
    0.88
    \'
    0.87
    umably
    0.86
    \'{
    0.85
     sees
    0.85
     lindo
    0.85
     nervously
    0.84
    POSITIVE LOGITS
     Environment
    0.87
     International
    0.86
     Special
    0.85
    Ᏻ
    0.81
     Miscellaneous
    0.81
     Organizational
    0.80
     Developing
    0.79
     Advertising
    0.79
     General
    0.78
     Development
    0.77
    Activations Density 0.003%

    No Known Activations