© 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. 13744
    Prev
    Next
    INDEX
    Explanations

    if you have a/an

    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
    ,
    -1.54
    一惊
    -1.48
     entrando
    -1.45
     撮り
    -1.42
     same
    -1.42
    melden
    -1.41
     avantages
    -1.39
     eſſ
    -1.36
    quite
    -1.30
     défis
    -1.30
    POSITIVE LOGITS
     such
    2.19
     that
    1.98
     this
    1.60
     any
    1.55
     your
    1.54
     which
    1.45
     those
    1.45
     izquierdo
    1.41
     large
    1.41
     it
    1.38
    Activations Density 0.038%

    No Known Activations