© 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. 72725
    Prev
    Next
    INDEX
    Explanations

    or is it?

    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
    </h3>
    -1.33
     المحت
    -1.24
    ERS
    -1.24
    mathrm
    -1.23
    ↵↵↵
    -1.20
     valamint
    -1.20
    片刻
    -1.19
     tchèque
    -1.19
    涤
    -1.18
    pography
    -1.17
    POSITIVE LOGITS
    注意事
    1.50
    Beispiele
    1.41
     Toilette
    1.34
     possesses
    1.34
     altered
    1.30
    llavero
    1.30
    Heil
    1.29
    Baik
    1.28
     dirancang
    1.27
     кислота
    1.26
    Activations Density 0.030%

    No Known Activations