© 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. 655
    Prev
    Next
    INDEX
    Explanations

    links ending in html

    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
     sulit
    1.72
     impres
    1.61
    сцю
    1.60
     Elytres
    1.47
     शिवाय
    1.45
     ";"
    1.43
     dada
    1.41
     आधा
    1.40
    ंधरा
    1.40
     incom
    1.39
    POSITIVE LOGITS
    h
    1.42
    WX
    1.41
    RW
    1.40
    세기
    1.39
    hwar
    1.39
    世紀
    1.37
    Visited
    1.34
    ement
    1.33
    igma
    1.33
    °
    1.32
    Activations Density 1.006%

    No Known Activations