© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 27
    Prev
    Next
    INDEX
    Explanations

    durations and time spans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
     समकक्ष
    0.95
    Average
    0.94
    运算符
    0.93
    운데
    0.89
    における
    0.86
     প্রতিনিধিদের
    0.84
    unakan
    0.83
    俱
    0.83
    appelijke
    0.83
     eşit
    0.82
    POSITIVE LOGITS
     awhile
    2.19
     decades
    2.09
     years
    1.96
     months
    1.88
     weeks
    1.82
     YEARS
    1.68
     centuries
    1.62
     ages
    1.58
     longer
    1.53
     hours
    1.48
    Activations Density 2.205%

    No Known Activations