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. 3637
    Prev
    Next
    INDEX
    Explanations

    programming keywords and commands

    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
    the
    1.86
    and
    1.84
    En
    1.81
    for
    1.78
    E
    1.77
    D
    1.75
    S
    1.72
    O
    1.72
    Is
    1.70
    from
    1.70
    POSITIVE LOGITS
     sushi
    1.78
     pizza
    1.71
     sonar
    1.69
     ssh
    1.67
     zu
    1.66
     ৪
    1.64
     nginx
    1.62
     oauth
    1.61
     mysql
    1.60
     anche
    1.60
    Activations Density 0.484%

    No Known Activations