© 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. 721
    Prev
    Next
    INDEX
    Explanations

    product listings

    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
    Ⴊ
    1.18
    𐱃
    1.15
    ര്‍ണ
    1.15
    𒐞
    1.14
    ꗟ
    1.14
    ಙ
    1.13
    ꗤ
    1.12
    ꗬ
    1.12
    𐰲
    1.12
    𒐤
    1.11
    POSITIVE LOGITS
     vac
    0.67
     //
    0.66
    </em>
    0.63
     than
    0.61
    ↵
    0.61
     เหรอ
    0.59
     تعالى
    0.57
     VICE
    0.56
     REVIEW
    0.56
    回事
    0.55
    Activations Density 0.285%

    No Known Activations