© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 43733
    Prev
    Next
    INDEX
    Explanations

    if-then consequence

    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
    ///</
    -1.88
    ᡳ
    -1.84
    didn
    -1.84
    絝
    -1.80
    ︲
    -1.78
     $-$
    -1.77
    (!__
    -1.75
    出了一
    -1.71
    __':
    -1.70
    )="
    -1.69
    POSITIVE LOGITS
     with
    2.73
     only
    2.27
     there
    2.16
     this
    2.06
     your
    2.03
     where
    2.00
     because
    1.97
     that
    1.94
     usually
    1.92
     selalu
    1.80
    Activations Density 0.015%

    No Known Activations