© 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. 970
    Prev
    Next
    INDEX
    Explanations

    measurements, time, or scores

    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
    a
    1.21
    assured
    0.88
    unknown
    0.84
    e
    0.83
     sh
    0.82
    window
    0.81
    aar
    0.81
    caller
    0.81
    heme
    0.80
    leads
    0.79
    POSITIVE LOGITS
    ्स
    1.04
    柩
    0.96
    晠
    0.94
    ನಲ್ಲಿ
    0.94
    作战
    0.94
    으로서
    0.94
    oleč
    0.93
     Nasional
    0.93
     życiu
    0.93
    äischen
    0.93
    Activations Density 0.125%

    No Known Activations