© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 718
    Prev
    Next
    INDEX
    Explanations

    places and activities

    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_16k_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
    ier
    0.81
    onomi
    0.80
    encial
    0.79
    ile
    0.73
    ü
    0.73
    ithmet
    0.72
    \
    0.71
    cc
    0.70
    end
    0.69
    ulative
    0.69
    POSITIVE LOGITS
     caves
    1.52
     Dinosaur
    1.45
     Caves
    1.44
     vineyards
    1.43
     wetlands
    1.43
     Cemetery
    1.40
     wineries
    1.40
     Lake
    1.40
     waterfalls
    1.39
     museums
    1.39
    Activations Density 0.729%

    No Known Activations