© 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. 1539
    Prev
    Next
    INDEX
    Explanations

    replete with experiences or events

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

    world, environment, paintings

    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
     consecutively
    0.45
     cosidd
    0.40
     स्थानांतर
    0.40
    groupby
    0.38
     astfel
    0.38
     Specifically
    0.38
     општи
    0.38
    켠
    0.37
     Relating
    0.37
    iffy
    0.37
    POSITIVE LOGITS
     punctuated
    1.04
     reminiscent
    1.00
     replete
    0.98
     worthy
    0.96
     steeped
    0.96
     brimming
    0.93
     rife
    0.93
     riddled
    0.91
     unmatched
    0.91
     fraught
    0.89
    Activations Density 0.438%

    No Known Activations