© 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. 43845
    Prev
    Next
    INDEX
    Explanations

    C++ and Java type declarations

    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
     and
    -2.64
     also
    -1.94
     of
    -1.84
     about
    -1.78
     to
    -1.73
     again
    -1.67
     then
    -1.64
    艄
    -1.55
    åter
    -1.53
    缡
    -1.52
    POSITIVE LOGITS
    _
    2.09
    what
    1.96
     bendera
    1.94
     hoher
    1.83
     kartun
    1.80
     Faced
    1.79
     boneka
    1.74
     What
    1.73
     mutiara
    1.71
     sayap
    1.71
    Activations Density 0.036%

    No Known Activations