© 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. 98204
    Prev
    Next
    INDEX
    Explanations

    racing and sports championships

    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
     their
    -1.61
     from
    -1.59
     as
    -1.49
     or
    -1.39
     ہیں
    -1.38
    室外
    -1.36
     by
    -1.28
     sociedades
    -1.19
     after
    -1.18
     espirituales
    -1.18
    POSITIVE LOGITS
     médec
    1.61
     fubject
    1.48
     difp
    1.44
     lavable
    1.41
     sains
    1.40
     réglementation
    1.40
     GRATU
    1.36
     ftate
    1.36
     dacia
    1.34
     reafon
    1.34
    Activations Density 0.032%

    No Known Activations