© 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. 13-GEMMASCOPE-2-RES-16K
    7. 905
    Prev
    Next
    INDEX
    Explanations

    listing items separated by commas

    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_13_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
    ະພັນ
    1.01
    ဆက်
    0.99
    स्फोट
    0.97
    ሰራ
    0.97
    َالَ
    0.95
     फ्रॉम
    0.94
    ێت
    0.94
    陬
    0.92
    લાઇ
    0.92
    ຖືກ
    0.92
    POSITIVE LOGITS
     and
    2.68
     và
    2.65
    และ
    2.54
    、
    2.47
     и
    2.46
    および
    2.37
     και
    2.35
     और
    2.34
     एवं
    2.31
     และ
    2.27
    Activations Density 1.890%

    No Known Activations