© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1802
    Prev
    Next
    INDEX
    Explanations

    hold back or to

    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
    рующий
    2.71
    ্যান্স
    2.45
    उंस
    2.44
    つけた
    2.30
    <bos>
    2.25
    awie
    2.24
    ouml
    2.21
    ﾞ
    2.20
    orgement
    2.19
    엽
    2.19
    POSITIVE LOGITS
    тие
    3.01
    thren
    2.88
    naires
    2.68
    Divid
    2.53
     tenir
    2.52
    gène
    2.52
    teenth
    2.50
    தா
    2.48
     ..."
    2.44
    violet
    2.43
    Activations Density 1.008%

    No Known Activations