© 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. 84705
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
     with
    -1.67
     on
    -1.60
     himself
    -1.43
     while
    -1.38
     encompasses
    -1.30
    entuh
    -1.29
     when
    -1.28
    Even
    -1.27
     for
    -1.27
    While
    -1.24
    POSITIVE LOGITS
    鸶
    1.42
     \{
    1.34
    ⍺
    1.21
     alpes
    1.20
    accharide
    1.17
    yled
    1.17
     และ
    1.16
     wsi
    1.16
    isst
    1.16
    acious
    1.15
    Activations Density 0.054%

    No Known Activations