© 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. 73190
    Prev
    Next
    INDEX
    Explanations

    fossil layers, geological time

    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
     impactos
    -1.44
    個室
    -1.41
    dė
    -1.38
     expectativa
    -1.31
     choice
    -1.31
     plausible
    -1.30
     different
    -1.29
     possible
    -1.29
     others
    -1.25
     usw
    -1.24
    POSITIVE LOGITS
     admirer
    1.41
     mayoría
    1.27
    狱
    1.23
     of
    1.22
     semua
    1.20
     emploi
    1.17
     Soit
    1.16
    лока
    1.15
     Influencer
    1.14
     acheteurs
    1.14
    Activations Density 0.035%

    No Known Activations