Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12100
    Prev
    Next
    INDEX
    Explanations

    recruitment

    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
    
    -1.09
    wendige
    -1.02
    娆
    -0.98
    oara
    -0.98
     turística
    -0.97
    жур
    -0.95
     vakantie
    -0.94
     prezent
    -0.94
     kovo
    -0.91
     yardım
    -0.89
    POSITIVE LOGITS
     needed
    0.94
     nachdem
    0.90
    tió
    0.88
     getRole
    0.84
     using
    0.84
     knew
    0.80
     seldom
    0.79
    ertale
    0.78
     berichtet
    0.78
     Replacement
    0.78
    Activations Density 0.001%

    No Known Activations