© 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. 1773
    Prev
    Next
    INDEX
    Explanations

    if n is negative

    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
     (…)
    1.23
     Important
    1.23
     şi
    1.22
     („
    1.21
     Beside
    1.19
     importantes
    1.18
     （
    1.17
     (=
    1.13
     Nowadays
    1.13
     corresponds
    1.13
    POSITIVE LOGITS
     honed
    1.19
     nays
    1.18
     sassy
    1.15
     goofy
    1.13
     tucked
    1.11
    诩
    1.11
     Newsom
    1.11
    Bonnie
    1.10
     Buffett
    1.09
     Mormon
    1.09
    Activations Density 0.027%

    No Known Activations