© 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. 22-GEMMASCOPE-RES-131K
    7. 72124
    Prev
    Next
    INDEX
    Explanations

    description of items

    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_22/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
     so
    -1.86
     what
    -1.24
     any
    -1.23
     That
    -1.23
     that
    -1.20
     Then
    -1.13
    するので
    -1.05
    那么
    -1.03
     this
    -1.02
     Whatever
    -1.00
    POSITIVE LOGITS
     and
    1.05
     subtil
    1.02
     relativ
    1.02
     والتي
    1.01
    前往
    0.97
     ſtre
    0.97
    ubscribe
    0.96
     professionally
    0.95
    iczne
    0.93
    hetics
    0.93
    Activations Density 0.003%

    No Known Activations