© 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. 4709
    Prev
    Next
    INDEX
    Explanations

    differences between

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

    list item definitions

    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
     ایک
    0.67
     پانچ
    0.63
    ኀ
    0.61
     جیسے
    0.61
     رکھا
    0.60
     تھے
    0.59
    📪
    0.58
     دونوں
    0.57
    ➵
    0.55
     تھے۔
    0.54
    POSITIVE LOGITS
     peculiarly
    1.07
     hebdom
    1.01
     erstwhile
    0.88
     volition
    0.86
     edifice
    0.85
     rattling
    0.84
     victimization
    0.82
     existent
    0.81
     instrumentality
    0.81
     effectual
    0.81
    Activations Density 0.450%

    No Known Activations