© 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. 989
    Prev
    Next
    INDEX
    Explanations

    cannot and will not

    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
    ฯ
    0.89
    в
    0.75
     које
    0.67
    А
    0.67
    ‌
    0.66
     مذکور
    0.64
    R
    0.63
    I
    0.63
    у
    0.63
    i
    0.62
    POSITIVE LOGITS
     durchaus
    1.01
     schönen
    0.97
     keiner
    0.96
     meteen
    0.96
     allerlei
    0.95
     etwas
    0.95
     hiç
    0.94
     tamamen
    0.94
     keinen
    0.93
     sogenannten
    0.93
    Activations Density 2.699%

    No Known Activations