© 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. 591
    Prev
    Next
    INDEX
    Explanations

    URLs and non-English characters

    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
    It
    1.28
    By
    1.21
    An
    1.21
     nigg
    1.20
    that
    1.20
    As
    1.15
    I
    1.15
    All
    1.14
    all
    1.14
    ist
    1.13
    POSITIVE LOGITS
     海
    2.42
     コットン
    2.36
     コーヒー
    2.35
     低
    2.28
     防水
    2.26
     キッズ
    2.24
     小型
    2.23
     香
    2.21
     ショルダーバッグ
    2.20
     食器
    2.20
    Activations Density 0.114%

    No Known Activations