© 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. 68106
    Prev
    Next
    INDEX
    Explanations

    quantities followed by units

    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
     tienda
    -1.40
    ‌.
    -1.31
    licopter
    -1.27
    parsedMessage
    -1.24
    itisation
    -1.23
     nuvem
    -1.23
    actéristi
    -1.22
    центри
    -1.20
     marav
    -1.19
    stander
    -1.19
    POSITIVE LOGITS
     that
    1.92
     like
    1.56
     from
    1.52
     bereits
    1.32
     must
    1.31
     out
    1.27
     on
    1.27
     Vertreter
    1.27
     cannot
    1.24
     erfolgreiche
    1.23
    Activations Density 0.061%

    No Known Activations