© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14890
    Prev
    Next
    INDEX
    Explanations

    offering more information

    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
    intestin
    2.23
     mapStateToProps
    2.02
    <unused577>
    1.95
    andelions
    1.91
    <unused1008>
    1.91
    <unused168>
    1.91
    říklad
    1.90
     devenit
    1.89
    <unused1968>
    1.88
    <unused1862>
    1.86
    POSITIVE LOGITS
    (
    1.32
     huh
    1.29
    Das
    1.24
    $$
    1.24
    صله
    1.21
    Non
    1.15
    anti
    1.13
    La
    1.12
    gle
    1.09
    Angel
    1.09
    Activations Density 0.112%

    No Known Activations