© 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. 29-GEMMASCOPE-2-RES-65K
    7. 5205
    Prev
    Next
    INDEX
    Explanations

    comma which

    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_29_width_65k_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
     Mother
    0.70
     mother
    0.66
    Mother
    0.63
    
    0.63
    シーズン
    0.62
     дорогу
    0.59
     meant
    0.58
     못
    0.58
     以
    0.58
     Project
    0.57
    POSITIVE LOGITS
     Hatton
    0.86
    фика
    0.84
    ipas
    0.83
    verg
    0.82
    поль
    0.81
    ственные
    0.81
     মনোনয়নপত্র
    0.80
    ibut
    0.79
     robuste
    0.79
     Татар
    0.78
    Activations Density 0.018%

    No Known Activations