© 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-262K
    7. 6062
    Prev
    Next
    INDEX
    Explanations

    break down

    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
    ות
    1.06
    Fluent
    1.03
    Questo
    1.03
     upravo
    1.03
    ুন
    0.99
    ധ്യമ
    0.97
    
    0.97
     ου
    0.96
    Value
    0.96
     متوسط
    0.96
    POSITIVE LOGITS
    irse
    1.19
    я
    1.18
    禕
    1.13
     creams
    1.12
     băng
    1.08
     dazz
    1.07
    ıyla
    1.06
     ballroom
    1.02
     subtract
    1.00
     refrigeration
    0.99
    Activations Density 0.000%

    No Known Activations