© 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. 60812
    Prev
    Next
    INDEX
    Explanations

    phrases starting clauses

    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
     TWENTY
    -1.98
     azonban
    -1.95
    biendo
    -1.88
    recently
    -1.86
    immediately
    -1.84
     perdiendo
    -1.80
    傒
    -1.77
    twenty
    -1.77
     cirugía
    -1.76
    婀
    -1.75
    POSITIVE LOGITS
     just
    1.74
     on
    1.58
     of
    1.56
     with
    1.45
     changed
    1.45
     possibly
    1.43
     without
    1.41
    是
    1.38
     and
    1.36
     shortly
    1.36
    Activations Density 0.097%

    No Known Activations