© 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. 69624
    Prev
    Next
    INDEX
    Explanations

    current state or status

    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
     similar
    -2.27
     then
    -1.59
     three
    -1.54
     similares
    -1.51
     those
    -1.50
     Similar
    -1.41
     know
    -1.35
     analogous
    -1.35
     what
    -1.32
     four
    -1.32
    POSITIVE LOGITS
     of
    1.54
     krä
    1.41
    นี้
    1.34
    rī
    1.33
     antigos
    1.30
     dinoss
    1.30
    ของ
    1.27
     subjek
    1.23
    idik
    1.23
     этого
    1.22
    Activations Density 0.321%

    No Known Activations