© 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. 610
    Prev
    Next
    INDEX
    Explanations

    break down

    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
    iate
    2.08
    <bos>
    1.90
    evice
    1.87
    iat
    1.86
    eal
    1.84
    ea
    1.78
    hang
    1.67
    aes
    1.67
    ാ
    1.66
    ió
    1.66
    POSITIVE LOGITS
     Grenzen
    1.79
    彡
    1.79
    स्यों
    1.78
    ⵕ
    1.72
    裟
    1.71
     ведь
    1.64
    স
    1.64
    ประสบการณ์
    1.64
    হেতু
    1.64
    Receive
    1.62
    Activations Density 0.263%

    No Known Activations