© 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. 8446
    Prev
    Next
    INDEX
    Explanations

    causes and effects

    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
    kleid
    -1.68
    kunjung
    -1.63
    蟳
    -1.60
    klare
    -1.59
     星空
    -1.58
     firſt
    -1.55
     тях
    -1.52
     posibles
    -1.52
    bestimm
    -1.52
    heiz
    -1.51
    POSITIVE LOGITS
     from
    2.67
     its
    2.19
     I
    2.13
     if
    1.94
     by
    1.91
     such
    1.90
     in
    1.73
     through
    1.73
     for
    1.70
     similar
    1.66
    Activations Density 0.074%

    No Known Activations