© 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. 7-GEMMASCOPE-2-RES-16K
    7. 495
    Prev
    Next
    INDEX
    Explanations

    Chinese character `踏`

    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
    d
    0.75
    m
    0.63
    ar
    0.62
    p
    0.62
    more
    0.59
    bust
    0.59
    k
    0.59
    meg
    0.59
    c
    0.56
    osar
    0.56
    POSITIVE LOGITS
     وهذا
    1.05
     وهو
    1.02
     considerando
    1.02
    MSFont
    1.01
     nějak
    1.01
     pavattati
    1.01
     TInner
    0.99
     tiež
    0.99
     }{}_{\
    0.99
     paccati
    0.99
    Activations Density 0.696%

    No Known Activations