© 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. 17-GEMMASCOPE-2-RES-16K
    7. 490
    Prev
    Next
    INDEX
    Explanations

    times of day greetings

    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_17_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
     காங்க
    0.96
     гене
    0.95
     epitope
    0.92
     சுற்றுச்சூழல்
    0.91
     egensk
    0.88
    hepat
    0.88
     चित्रित
    0.87
    Ꮘ
    0.86
     статті
    0.85
     रै
    0.85
    POSITIVE LOGITS
     noon
    3.42
     midnight
    3.34
     midday
    3.27
     evening
    3.25
     afternoon
    3.23
     morning
    3.18
     오후
    3.16
     lunchtime
    2.95
     Noon
    2.94
    中午
    2.92
    Activations Density 2.464%

    No Known Activations