© 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. 118827
    Prev
    Next
    INDEX
    Explanations

    follows punctuation

    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
     neither
    -0.94
    ť
    -0.93
     เขา
    -0.93
     cuartos
    -0.92
     ulica
    -0.90
     enfans
    -0.90
    壅
    -0.90
     voltaje
    -0.90
     producenta
    -0.90
     दोनों
    -0.90
    POSITIVE LOGITS
     again
    1.18
     majority
    1.05
     it
    1.04
     this
    1.02
     above
    1.00
    Again
    0.94
     apart
    0.93
     Again
    0.93
     допусти
    0.91
     sebelum
    0.89
    Activations Density 0.012%

    No Known Activations