© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10430
    Prev
    Next
    INDEX
    Explanations

    senior job titles and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ந்தைய
    0.99
    ग्
    0.98
    daemon
    0.93
    ra
    0.92
    जू
    0.92
    टे
    0.90
     Beginn
    0.89
    ệ
    0.89
    ού
    0.88
    young
    0.87
    POSITIVE LOGITS
     citizens
    1.60
     citizen
    1.56
     statesman
    1.45
    citizen
    1.41
     citiz
    1.36
    citizens
    1.34
     statesmen
    1.32
     Citizens
    1.22
    Citizen
    1.21
     Citizen
    1.17
    Activations Density 0.046%

    No Known Activations