© 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. 1496
    Prev
    Next
    INDEX
    Explanations

    describing states of being

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

    simultaneously contrasting qualities

    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
     dość
    0.48
    かなり
    0.47
     oldukça
    0.44
    都很
    0.43
     काफी
    0.43
    すごく
    0.43
     khá
    0.42
    꽤
    0.41
     довольно
    0.40
    我很
    0.40
    POSITIVE LOGITS
     imbued
    0.84
     fundamentally
    0.83
     inescap
    0.78
     inextricably
    0.76
     unmistak
    0.71
     permeated
    0.67
     emphatically
    0.66
     irrevoc
    0.65
     replete
    0.65
     inseparable
    0.64
    Activations Density 0.492%

    No Known Activations