© 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. 14163
    Prev
    Next
    INDEX
    Explanations

    extended reality (VR, AR, MR)

    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
    𝐚
    2.05
    𝐭
    1.97
     "&#
    1.88
    isible
    1.87
     ВО
    1.84
     equidistant
    1.83
     solemnly
    1.81
    ޭ
    1.80
    ሷ
    1.79
     sensible
    1.79
    POSITIVE LOGITS
    انی
    2.03
     परीक्ष
    2.00
    lichkeit
    1.85
    ந்த
    1.77
    ObjectID
    1.74
    ший
    1.74
    яд
    1.71
     pull
    1.71
    sman
    1.68
    솎
    1.67
    Activations Density 0.034%

    No Known Activations