© 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. 44130
    Prev
    Next
    INDEX
    Explanations

    how something came to be

    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
     också
    -1.64
    觧
    -1.59
     jejich
    -1.56
     Municipalidad
    -1.53
    </h3>
    -1.49
     PUSTAKA
    -1.46
     utilisée
    -1.45
    他们的
    -1.45
     flera
    -1.44
     jiné
    -1.41
    POSITIVE LOGITS
     innen
    1.41
     but
    1.34
    Toponymie
    1.33
    s
    1.29
     a
    1.24
     this
    1.23
     internet
    1.23
     in
    1.23
    1.15
     so
    1.14
    Activations Density 0.033%

    No Known Activations