© 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. 4893
    Prev
    Next
    INDEX
    Explanations

    filling a gap

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

    identifying knowledge gaps

    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
     toast
    0.40
    တီ
    0.37
    આત
    0.36
    掸
    0.35
     Vil
    0.34
    leiter
    0.34
    imist
    0.33
     Побе
    0.33
    irii
    0.33
     Sitt
    0.33
    POSITIVE LOGITS
     gap
    4.84
    gap
    4.50
    Gap
    4.41
     gaps
    4.41
     Gap
    4.38
     GAP
    3.77
    GAP
    3.58
    갭
    2.91
    隙
    2.72
    差距
    2.41
    Activations Density 0.147%

    No Known Activations