© 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. 7-GEMMASCOPE-2-RES-16K
    4. 14439
    Prev
    Next
    INDEX
    Explanations

    Mesoamerican to Strike

    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
    徊
    1.67
     bine
    1.66
     ba
    1.59
     dica
    1.50
     fa
    1.50
    iles
    1.45
    ंखला
    1.44
     منت
    1.43
    arly
    1.41
    شهر
    1.39
    POSITIVE LOGITS
    s
    3.15
    了
    2.66
    sman
    2.65
    मिताभ
    2.60
    いる
    2.57
    нкү
    2.39
    <bos>
    2.35
    ことができる
    2.31
    sne
    2.31
    空気
    2.30
    Activations Density 16.232%

    No Known Activations