© 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. 21526
    Prev
    Next
    INDEX
    Explanations

    measures as function of

    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
     cordones
    -1.49
     zoude
    -1.38
    ">
    -1.30
     SERV
    -1.28
    了许多
    -1.25
     ſever
    -1.24
     dieß
    -1.24
     ſta
    -1.24
     who
    -1.23
     sâ
    -1.23
    POSITIVE LOGITS
     on
    1.61
     including
    1.53
     permitirá
    1.47
    Some
    1.36
    During
    1.34
     allows
    1.34
     reír
    1.34
     explicado
    1.34
     genética
    1.34
     allow
    1.34
    Activations Density 0.155%

    No Known Activations