© 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. 69903
    Prev
    Next
    INDEX
    Explanations

    during decades

    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
     what
    -1.47
     Currently
    -1.37
     that
    -1.30
     This
    -1.30
     Besides
    -1.26
     Aside
    -1.24
     Unlike
    -1.23
     over
    -1.23
     When
    -1.22
     nâu
    -1.22
    POSITIVE LOGITS
     herstellen
    1.40
    ties
    1.30
     verbinden
    1.27
     rasch
    1.26
    ulates
    1.23
     rése
    1.22
    perhaps
    1.21
     hisz
    1.20
    s
    1.20
     costos
    1.16
    Activations Density 0.082%

    No Known Activations