© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21747
    Prev
    Next
    INDEX
    Explanations

    gauge what to change

    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
     although
    -1.45
     from
    -1.42
     after
    -1.38
     three
    -1.32
     despite
    -1.30
     as
    -1.29
     because
    -1.20
     previous
    -1.16
     予約
    -1.12
     while
    -1.11
    POSITIVE LOGITS
     your
    1.39
    ässer
    1.34
    atorias
    1.24
    tieron
    1.22
     ___________
    1.21
    תיים
    1.20
    PLICATION
    1.17
    /
    1.16
    onien
    1.16
     nobre
    1.13
    Activations Density 0.277%

    No Known Activations