© 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. 67540
    Prev
    Next
    INDEX
    Explanations

    not followed by a word

    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
     will
    -1.42
    section
    -1.40
    these
    -1.33
     вашу
    -1.30
    另外
    -1.29
    るのは
    -1.27
    ed
    -1.25
     first
    -1.23
     ABOUT
    -1.23
    儈
    -1.23
    POSITIVE LOGITS
     fuimos
    1.77
     that
    1.72
    ToRemove
    1.69
    Elaboración
    1.59
    ="")
    1.56
    ditionally
    1.55
     específicas
    1.52
     teníamos
    1.52
     tinham
    1.51
     tiveram
    1.50
    Activations Density 0.065%

    No Known Activations