© 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. 13-GEMMASCOPE-2-RES-16K
    7. 1084
    Prev
    Next
    INDEX
    Explanations

    code comments and logic

    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_13_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
    𝗴
    2.12
    ᠮ
    2.07
    ḓ
    2.06
     challenging
    2.06
    遉
    2.02
    𝗿
    1.99
    ╅
    1.99
    ет
    1.98
    𝗱
    1.97
    ᆯ
    1.97
    POSITIVE LOGITS
    xFF
    2.56
    xff
    2.24
    xffff
    1.80
    xFFFF
    1.73
    Aw
    1.69
    ة
    1.63
    xc
    1.60
     RouterModule
    1.59
    ⁧
    1.59
    AAC
    1.52
    Activations Density 0.265%

    No Known Activations