© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1849
    Prev
    Next
    INDEX
    Explanations

    HTML element selectors

    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_17_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
     legitimate
    0.86
    ­
    0.84
     laying
    0.83
     Western
    0.82
     ​​
    0.81
     articulated
    0.80
     mainstream
    0.80
     giving
    0.80
     substantive
    0.79
    ‐
    0.79
    POSITIVE LOGITS
    等地
    1.22
    கல்
    1.21
     sebagainya
    1.16
    诹
    1.15
    centaje
    1.13
    ష్
    1.12
    就连
    1.11
    ົບ
    1.11
    ພາບ
    1.11
    exitTool
    1.10
    Activations Density 0.247%

    No Known Activations