© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 9374
    Prev
    Next
    INDEX
    Explanations

    new followed by a noun

    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
    n
    3.15
    tat
    3.12
    t
    3.12
    rd
    3.07
    tak
    2.88
    nement
    2.71
    nya
    2.63
    tum
    2.59
    ship
    2.58
    ra
    2.57
    POSITIVE LOGITS
    <bos>
    3.10
    ี่ยง
    3.08
    istä
    3.00
    न्द्रीय
    2.95
    वानिव
    2.88
    ஞ்ஞான
    2.73
    ৗ
    2.67
    ็น
    2.61
    সরকারী
    2.59
    හෙ
    2.57
    Activations Density 2.033%

    No Known Activations