© 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. 39004
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

    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
     it
    -1.72
     These
    -1.70
     They
    -1.57
    b
    -1.56
    d
    -1.52
    an
    -1.50
     esses
    -1.45
    h
    -1.45
    k
    -1.43
    f
    -1.39
    POSITIVE LOGITS
    ARIOS
    1.54
     ajudá
    1.53
     serão
    1.52
    sellor
    1.52
     löytyy
    1.49
     ocorrer
    1.48
     precisamos
    1.48
     oplossing
    1.46
     our
    1.44
     procurando
    1.41
    Activations Density 0.198%

    No Known Activations