Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 1565
    Prev
    Next
    INDEX
    Explanations

    'captain' and 'normandy'

    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
    MktCap
    0.73
    SLASH
    0.68
    DeathRecord
    0.67
    OCKET
    0.66
     matematik
    0.66
    
    0.66
    rooted
    0.65
    _/
    0.65
     separación
    0.65
     ആശയ
    0.65
    POSITIVE LOGITS
     Inhib
    0.80
     corporations
    0.70
     אוי
    0.69
     titular
    0.68
     अनुर
    0.66
     corporation
    0.64
    詁
    0.64
    Superview
    0.64
     Nora
    0.64
     আর্
    0.63
    Activations Density 0.027%

    No Known Activations