© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 697
    Prev
    Next
    INDEX
    Explanations

    list items signaled by asterisks

    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
     the
    1.40
     a
    1.37
    1.30
     (
    1.28
     and
    1.24
     or
    1.23
     I
    1.23
    -
    1.22
     is
    1.18
     present
    1.17
    POSITIVE LOGITS
    𒅇
    2.66
    𒈫
    2.65
    𒈣
    2.63
    𒌐
    2.63
    𒃷
    2.63
    𒉪
    2.62
    𒀌
    2.61
    𒊕
    2.61
    𒌜
    2.61
    𒉣
    2.61
    Activations Density 0.020%

    No Known Activations