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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11328
    Prev
    Next
    INDEX
    Explanations

    SCADA, Waldenström, Trappers, Announcements, Multiattribute

    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
     Allí
    -1.39
     Había
    -1.38
    essment
    -1.36
     tocado
    -1.34
    blouse
    -1.34
     arrancar
    -1.30
     Incluso
    -1.28
     Direktur
    -1.26
     Tampoco
    -1.25
     朝食
    -1.20
    POSITIVE LOGITS
     &
    1.27
    </h2>
    1.17
     Ref
    1.09
     permitiendo
    1.05
    Tor
    1.02
     косме
    1.01
     României
    1.01
    hi
    1.00
                 
    1.00
     />
    1.00
    Activations Density 0.006%

    No Known Activations