© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 5043
    Prev
    Next
    INDEX
    Explanations

    watches and smartwatches

    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_262k_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
     abortion
    0.85
    議員
    0.78
     Abortion
    0.74
     Youn
    0.74
     sesu
    0.72
    鄢
    0.72
     destruct
    0.71
     impeach
    0.71
     muebles
    0.71
     Tenant
    0.71
    POSITIVE LOGITS
     smartwatch
    1.89
     timepiece
    1.86
     wristwatch
    1.72
     Seiko
    1.71
     Rolex
    1.64
     chronograph
    1.60
    watches
    1.60
     reloj
    1.60
    錶
    1.59
     watches
    1.58
    Activations Density 0.045%

    No Known Activations