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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8712
    Prev
    Next
    INDEX
    Explanations

    high and low intensity

    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
    ledning
    -0.74
    página
    -0.73
     selera
    -0.72
    ᑯ
    -0.72
    夸张
    -0.71
    culus
    -0.69
    izier
    -0.68
     пато
    -0.67
     irritating
    -0.66
    рма
    -0.66
    POSITIVE LOGITS
     high
    3.80
    high
    3.30
    High
    2.97
    高
    2.75
     High
    2.63
    HIGH
    2.59
     HIGH
    2.34
     low
    1.87
     高
    1.79
     yüksek
    1.77
    Activations Density 0.053%

    No Known Activations