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. 8607
    Prev
    Next
    INDEX
    Explanations

    Greek mythological names

    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
     associative
    -0.77
     artistry
    -0.77
     reactivity
    -0.73
     Ratna
    -0.73
     conformal
    -0.73
    Ǝ
    -0.73
    etro
    -0.73
     jeszcze
    -0.73
     Messing
    -0.72
     ospiti
    -0.71
    POSITIVE LOGITS
    odb
    0.77
     Artemis
    0.75
    Jou
    0.73
     Goddess
    0.72
    ordes
    0.71
     Greece
    0.69
    inin
    0.69
    ✥
    0.69
     Jou
    0.69
     Greek
    0.68
    Activations Density 0.028%

    No Known Activations