© 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. 110557
    Prev
    Next
    INDEX
    Explanations

    size and dimension measurements

    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
    towym
    -0.69
     inset
    -0.68
     despise
    -0.67
     devaluation
    -0.65
    CONSTANT
    -0.63
    飒
    -0.63
     berupa
    -0.63
     onward
    -0.62
     خانه
    -0.62
     geb
    -0.61
    POSITIVE LOGITS
     longest
    1.83
    longest
    1.74
     widest
    1.64
     maximum
    1.61
     diameter
    1.50
     greatest
    1.48
    maximum
    1.42
    Longest
    1.42
     axis
    1.41
     largest
    1.39
    Activations Density 0.095%

    No Known Activations