© 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. 774
    Prev
    Next
    INDEX
    Explanations

    self-

    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
    pas
    2.42
    णिज्य
    2.36
    िक्रमा
    2.22
    ᠠ
    2.20
    NetAmount
    2.19
    ッジ
    2.17
    igrade
    2.15
    NuGetPackage
    2.14
    Intersect
    2.14
     seguirá
    2.13
    POSITIVE LOGITS
    verständlich
    2.36
    ies
    2.16
    argv
    2.06
    ിവ
    2.06
    シャル
    2.03
    holtz
    2.02
    າຍ
    2.02
    <bos>
    2.01
    ي
    2.01
    いたら
    1.99
    Activations Density 1.348%

    No Known Activations