© 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. 63
    Prev
    Next
    INDEX
    Explanations

    David Graham

    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
     nirvach
    2.09
    rparam
    2.03
    <unused1244>
    2.01
    sunline
    2.01
    lanelet
    2.01
    cparam
    2.00
    <unused1833>
    2.00
    nBitCount
    1.97
    discrete
    1.97
    bokeh
    1.96
    POSITIVE LOGITS
    '
    2.19
    ’
    2.00
    ia
    1.67
     Joseph
    1.55
     Price
    1.54
     Samuel
    1.51
     Brothers
    1.46
     Th
    1.46
     John
    1.46
     M
    1.45
    Activations Density 3.525%

    No Known Activations