© 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. 7595
    Prev
    Next
    INDEX
    Explanations

    looking for a way to

    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
     одну
    -1.49
     tirantes
    -1.45
     one
    -1.45
     یکی
    -1.28
     choisi
    -1.27
     один
    -1.24
     одного
    -1.22
     bolsillos
    -1.19
     asientos
    -1.19
    wigs
    -1.18
    POSITIVE LOGITS
     to
    2.42
     cumpli
    1.46
     ktorí
    1.39
     when
    1.38
     in
    1.34
     guidance
    1.33
     who
    1.31
    ßung
    1.29
     help
    1.29
     which
    1.28
    Activations Density 0.110%

    No Known Activations