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. 110209
    Prev
    Next
    INDEX
    Explanations

    stock tickers and financial news

    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
    CREATED
    -0.74
    Dns
    -0.73
    felder
    -0.73
    лык
    -0.73
    Fond
    -0.73
    ReLU
    -0.71
     coven
    -0.70
    ৮
    -0.70
     Siamo
    -0.70
     Galla
    -0.70
    POSITIVE LOGITS
     reverse
    1.09
     symbol
    0.84
     Merger
    0.81
    NQ
    0.80
    iterrane
    0.80
    Reverse
    0.79
     offering
    0.79
    ønne
    0.76
     ámbito
    0.75
    reverse
    0.74
    Activations Density 0.063%

    No Known Activations