© 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. 34-GEMMASCOPE-RES-131K
    7. 109835
    Prev
    Next
    INDEX
    Explanations

    questions starting with Q:

    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_34/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
     图案
    -0.84
    felizmente
    -0.79
     Ebola
    -0.78
     Kach
    -0.77
     menga
    -0.77
    ‶
    -0.76
     ingest
    -0.76
     Pura
    -0.76
     GW
    -0.75
     everybody
    -0.74
    POSITIVE LOGITS
     Tallahassee
    0.93
    Thunder
    0.80
    pine
    0.80
     calcular
    0.80
    كان
    0.80
     Även
    0.80
    Sand
    0.80
    Shock
    0.77
     ad
    0.75
    Lead
    0.74
    Activations Density 0.001%

    No Known Activations