© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14464
    Prev
    Next
    INDEX
    Explanations

    System.out

    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_7_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
    轅
    2.84
    InSection
    2.67
    ृह
    2.63
     पंत
    2.62
    holen
    2.60
     guessed
    2.56
    eglasses
    2.55
    ="#!"
    2.49
    Экс
    2.46
    δος
    2.46
    POSITIVE LOGITS
    ০
    3.44
    ا
    3.40
    יות
    3.40
    ੀ
    3.24
    י
    3.22
    lc
    2.93
    ာ
    2.83
    er
    2.80
    tied
    2.73
    eries
    2.71
    Activations Density 0.017%

    No Known Activations