© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1609
    Prev
    Next
    INDEX
    Explanations

    what we can

    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_65k_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
     part
    0.63
     wielu
    0.63
     zahlreiche
    0.60
     utrzym
    0.60
    ্কর
    0.59
     numerosos
    0.58
    n
    0.58
     many
    0.57
    قار
    0.57
     몇
    0.57
    POSITIVE LOGITS
    iotic
    0.77
    indrome
    0.75
    icode
    0.73
    ﾕ
    0.70
    destructive
    0.69
    Пре
    0.68
    Ｍ
    0.67
    кә
    0.67
    岁的
    0.67
    Gaming
    0.67
    Activations Density 1.510%

    No Known Activations