© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20537
    Prev
    Next
    INDEX
    Explanations

    conditional or future statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utford
    -1.63
    𓐍
    -1.46
     sánchez
    -1.37
     tuta
    -1.36
     will
    -1.33
    鞄
    -1.33
    క్ష
    -1.30
    Ⴀ
    -1.30
     bús
    -1.29
    !***
    -1.28
    POSITIVE LOGITS
     from
    2.06
    <strong>
    1.15
    (
    1.13
    最初に
    1.13
     or
    1.13
     gewesen
    1.13
     system
    1.09
     endlich
    1.09
    isClosed
    1.09
    จาก
    1.08
    Activations Density 0.142%

    No Known Activations