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. 3692
    Prev
    Next
    INDEX
    Explanations

    prefix + suffix word formation

    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
    ment
    0.65
    ing
    0.56
    d
    0.51
    ation
    0.49
    ible
    0.48
    ively
    0.48
    izing
    0.47
    z
    0.47
    ingly
    0.46
    
    0.44
    POSITIVE LOGITS
     Termination
    0.53
     Operand
    0.53
     Compose
    0.53
     Plugins
    0.51
     Teeth
    0.50
     Interface
    0.50
     Bakery
    0.49
     inhomogeneity
    0.49
     Footer
    0.49
     Slate
    0.49
    Activations Density 0.210%

    No Known Activations