© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73659
    Prev
    Next
    INDEX
    Explanations

    sports contexts

    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_22/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
     now
    -1.17
     maail
    -1.16
     ormai
    -1.13
    Since
    -1.12
    Every
    -1.10
    Because
    -1.09
     it
    -1.06
     personalmente
    -1.05
     so
    -1.05
    These
    -1.04
    POSITIVE LOGITS
     in
    1.38
     with
    1.30
     throughout
    1.27
    éndose
    1.22
     early
    1.16
     mą
    1.10
     وكان
    1.09
    fillment
    1.09
    高端
    1.08
    hores
    1.07
    Activations Density 0.023%

    No Known Activations