© 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. 7-GEMMASCOPE-2-RES-16K
    7. 244
    Prev
    Next
    INDEX
    Explanations

    types of parts or components

    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_7_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
    <unused1203>
    1.86
    <unused872>
    1.85
    𒁲
    1.84
    Pyrazole
    1.83
    𐰣
    1.81
     "????.??.??"]
    1.80
     Органи
    1.80
    <unused815>
    1.80
    <unused939>
    1.80
     Appodeal
    1.80
    POSITIVE LOGITS
    '
    1.29
     aircraft
    1.20
    -
    1.19
     dealership
    1.15
     automobile
    1.15
     and
    1.13
     chassis
    1.10
     or
    1.08
     automobiles
    1.02
     with
    1.02
    Activations Density 4.680%

    No Known Activations