© 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. 10164
    Prev
    Next
    INDEX
    Explanations

    to

    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
     emulsions
    1.05
     decomposition
    1.02
    信する
    1.02
    羿
    0.99
    )#
    0.99
    MORD
    0.98
     murderers
    0.98
    سٹم
    0.97
    줌
    0.97
    െയി
    0.95
    POSITIVE LOGITS
    were
    1.03
    loud
    0.99
    टान
    0.98
    grou
    0.97
    peak
    0.96
    控股
    0.95
    κό
    0.95
    ר
    0.94
    ibur
    0.93
    Purch
    0.93
    Activations Density 0.000%

    No Known Activations