© 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. 60615
    Prev
    Next
    INDEX
    Explanations

    widely different

    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
     “
    -1.48
    ="&#
    -1.26
    ある
    -1.21
    恙
    -1.21
    милия
    -1.21
    mín
    -1.20
    迸
    -1.19
    También
    -1.19
    лайд
    -1.18
    zboi
    -1.17
    POSITIVE LOGITS
     how
    1.52
     the
    1.27
     different
    1.26
     olika
    1.23
     completamente
    1.23
     that
    1.19
    different
    1.15
    劭
    1.13
     diferença
    1.13
     einst
    1.13
    Activations Density 0.096%

    No Known Activations