© 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. 67221
    Prev
    Next
    INDEX
    Explanations

    published herein

    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
     CHAIR
    -1.64
    corresponding
    -1.45
    桖
    -1.40
     conduce
    -1.39
     Minist
    -1.39
     europa
    -1.38
     lendemain
    -1.38
     azule
    -1.37
     gea
    -1.35
     activer
    -1.34
    POSITIVE LOGITS
     this
    2.80
     that
    2.52
     him
    2.13
     or
    1.84
     other
    1.83
     from
    1.82
     on
    1.77
     these
    1.77
     such
    1.76
     it
    1.64
    Activations Density 0.114%

    No Known Activations