© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10111
    Prev
    Next
    INDEX
    Explanations

    www. shopping. public

    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_22_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
     percentages
    1.02
    getToken
    0.94
    rategy
    0.94
    rifice
    0.92
     disturbed
    0.92
     $\%$
    0.89
    mixin
    0.89
    ்த்து
    0.88
    ترى
    0.87
    TERY
    0.87
    POSITIVE LOGITS
    ocirc
    0.99
    ège
    0.92
    ical
    0.90
     मेघ
    0.89
    ico
    0.89
    ebut
    0.86
    ney
    0.84
    sey
    0.83
    ICAL
    0.82
    际
    0.82
    Activations Density 0.052%

    No Known Activations