© 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. 1586
    Prev
    Next
    INDEX
    Explanations

    sustainable and blood contexts

    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
    <unused909>
    2.84
    焽
    2.71
    subfigure
    2.66
    䞍
    2.61
    ":(
    2.59
    <unused1279>
    2.56
     कंटिन्यू
    2.53
    роне
    2.52
    ină
    2.51
    〃
    2.50
    POSITIVE LOGITS
    nt
    2.59
    sa
    2.04
    nd
    1.91
     it
    1.85
     ic
    1.84
     آپ
    1.82
     u
    1.76
    nte
    1.76
    m
    1.75
     ib
    1.73
    Activations Density 0.477%

    No Known Activations