© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14927
    Prev
    Next
    INDEX
    Explanations

    TRE ME

    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
    тні
    2.16
    olič
    2.10
     parlé
    2.04
    例文
    2.02
     malesuada
    2.02
    विड़
    2.00
    т
    1.96
    ्रीम
    1.95
    aggo
    1.95
    ård
    1.95
    POSITIVE LOGITS
    𝐥
    2.07
    𝐧
    2.07
    че
    1.95
    iliated
    1.88
    𝐬
    1.87
    𝐮
    1.82
    𝐩
    1.79
     native
    1.78
    არე
    1.77
     з
    1.77
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.