© 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. 34-GEMMASCOPE-RES-131K
    7. 64300
    Prev
    Next
    INDEX
    Explanations

    defendant

    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_34/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
     what
    -2.19
     really
    -1.66
     like
    -1.62
     Really
    -1.58
    ignment
    -1.57
     to
    -1.52
     people
    -1.49
     certain
    -1.48
     in
    -1.46
     tremendously
    -1.46
    POSITIVE LOGITS
    -
    2.17
     cuadrado
    1.68
     flotte
    1.60
     kalender
    1.60
     meub
    1.59
     outils
    1.54
     étag
    1.52
     dette
    1.50
     murale
    1.48
     plafon
    1.48
    Activations Density 0.364%

    No Known Activations