© 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. 14507
    Prev
    Next
    INDEX
    Explanations

    go code

    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
    s
    4.57
    ا
    4.40
    此之外
    3.91
    sion
    3.73
    ところが
    3.57
    ો
    3.55
    tions
    3.41
    ्स
    3.40
    י
    3.38
    ところに
    3.38
    POSITIVE LOGITS
    ğ
    2.87
    ed
    2.62
    urgie
    2.48
    𝓈
    2.47
    وط
    2.45
    ynos
    2.44
    üğ
    2.42
     t
    2.41
    bells
    2.38
    ede
    2.37
    Activations Density 0.026%

    No Known Activations