© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1711
    Prev
    Next
    INDEX
    Explanations

    performance task assessment

    np_acts-logits-general · gemini-2.5-flash-lite

    official company name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    ဆုံး
    0.41
     CONCLUS
    0.41
     equipado
    0.39
     Fried
    0.39
     conto
    0.38
    Depart
    0.38
    ទេស
    0.37
    ዬ
    0.37
     Sails
    0.37
    SearchCV
    0.37
    POSITIVE LOGITS
     disciplinary
    0.79
    Performance
    0.75
     Performance
    0.73
     Dis
    0.71
     performance
    0.70
    performance
    0.68
     Clar
    0.68
     Science
    0.66
     Assessment
    0.66
    Science
    0.65
    Activations Density 0.010%

    No Known Activations