© 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. 608
    Prev
    Next
    INDEX
    Explanations

    tell me to tailor

    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
    ﺏ
    1.96
    ರಿಸ
    1.84
    ডার
    1.78
    ጨማሪ
    1.76
    ーストラ
    1.75
     जन्म
    1.75
     intérêts
    1.75
    फारिश
    1.72
    嶙
    1.70
     personagens
    1.67
    POSITIVE LOGITS
    <bos>
    2.03
    ContentLoaded
    1.99
     deep
    1.71
     attic
    1.68
    闱
    1.58
    ∖
    1.54
    ია
    1.53
    壢
    1.52
    訌
    1.50
    闼
    1.50
    Activations Density 0.915%

    No Known Activations