© 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. 22-GEMMASCOPE-2-RES-16K
    7. 192
    Prev
    Next
    INDEX
    Explanations

    break down

    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_22_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
     Tiet
    0.62
     hinzu
    0.60
     headings
    0.59
     microtub
    0.59
    鈾
    0.59
     idiom
    0.58
    startsWith
    0.57
     cooperated
    0.57
    ሆ
    0.57
    testX
    0.56
    POSITIVE LOGITS
    znac
    0.78
     Sé
    0.72
    〰
    0.69
    znacz
    0.66
    pportune
    0.65
    nab
    0.64
    nb
    0.64
     ন্যাশনাল
    0.64
    年輕
    0.63
    xf
    0.63
    Activations Density 1.315%

    No Known Activations