© 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. 14450
    Prev
    Next
    INDEX
    Explanations

    events following timed

    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
    ため
    2.90
    𝗲
    2.88
    𝗶
    2.71
    కు
    2.71
    蒾
    2.66
    Depends
    2.47
    ى
    2.46
    ર
    2.38
    𝙚
    2.37
    s
    2.36
    POSITIVE LOGITS
    ᐟ
    3.71
    jpg
    3.25
    removeAttribute
    2.62
    ोले
    2.61
    hede
    2.36
    jpe
    2.32
    edt
    2.30
    counter
    2.28
    exe
    2.28
    ઓ
    2.27
    Activations Density 0.003%

    No Known Activations