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. 8583
    Prev
    Next
    INDEX
    Explanations

    saving, creating, adding

    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
    buh
    -0.78
    ervos
    -0.77
     findViewById
    -0.76
    琥
    -0.76
    service
    -0.74
    ledo
    -0.74
    éroport
    -0.73
    raje
    -0.73
    <()>
    -0.72
    ANDRO
    -0.71
    POSITIVE LOGITS
     save
    2.06
     saves
    1.99
    save
    1.95
     saved
    1.80
     saving
    1.76
    Save
    1.60
     Save
    1.48
    Saves
    1.46
     Saves
    1.46
    SAVE
    1.45
    Activations Density 0.002%

    No Known Activations