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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7851
    Prev
    Next
    INDEX
    Explanations

    King followed by proper nouns or descriptors

    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
    されている
    -0.90
     aceites
    -0.89
    おすすめの
    -0.88
    inetics
    -0.77
    等于
    -0.73
     stiff
    -0.72
     flüs
    -0.71
     caffe
    -0.71
     juices
    -0.70
    に関して
    -0.70
    POSITIVE LOGITS
    👑
    1.49
    pin
    1.20
    STON
    1.19
     Cobra
    1.08
    size
    1.08
    King
    1.05
    kong
    1.05
    fisher
    1.05
     cobra
    1.05
     kong
    1.02
    Activations Density 0.028%

    No Known Activations