© 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. 118619
    Prev
    Next
    INDEX
    Explanations

    file paths and joining

    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
     that
    -1.01
     Vertra
    -1.01
     true
    -0.99
     along
    -0.98
     having
    -0.95
     through
    -0.91
     /
    -0.91
     only
    -0.90
     because
    -0.90
    来店
    -0.89
    POSITIVE LOGITS
     tabac
    1.18
     '..
    0.96
     "..
    0.94
     Aguas
    0.93
    ","
    0.91
     ELECTRIC
    0.90
    нией
    0.90
    ،
    0.89
     violences
    0.89
     ↓,
    0.89
    Activations Density 0.005%

    No Known Activations