© 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. 10-GEMMASCOPE-RES-131K
    7. 519
    Prev
    Next
    INDEX
    Explanations

    people or ranks

    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
    satisfies
    -1.18
        
    -1.17
     cit
    -1.16
     descri
    -1.16
    ListOf
    -1.14
     gabbana
    -1.13
    ⏎
    -1.13
     summarizes
    -1.13
    =[[
    -1.13
     part
    -1.12
    POSITIVE LOGITS
     údaje
    1.23
     informace
    1.20
     человек
    1.12
     sienten
    1.11
    
    1.10
     não
    1.10
     them
    1.10
     bílé
    1.09
     keinen
    1.08
    čne
    1.08
    Activations Density 0.158%

    No Known Activations