© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85840
    Prev
    Next
    INDEX
    Explanations

    numbers separated by commas

    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
    ኧ
    -1.91
     vegano
    -1.77
    Seznam
    -1.73
     sincero
    -1.73
    ilige
    -1.72
    谖
    -1.72
     bilde
    -1.70
    Elektron
    -1.69
    何故
    -1.66
     feitas
    -1.66
    POSITIVE LOGITS
     who
    1.79
     while
    1.77
     with
    1.74
     These
    1.73
     as
    1.68
     but
    1.68
     on
    1.63
     We
    1.62
     With
    1.62
     While
    1.61
    Activations Density 0.001%

    No Known Activations