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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8205
    Prev
    Next
    INDEX
    Explanations

    places and destinations

    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
     детские
    -0.94
    brtc
    -0.90
    ígenes
    -0.81
    potranspiration
    -0.81
    こちらが
    -0.79
    灵活
    -0.77
     gewin
    -0.77
     acabou
    -0.76
     fachada
    -0.76
    を入
    -0.76
    POSITIVE LOGITS
     dentist
    1.70
     library
    1.52
     supermarket
    1.45
     movies
    1.44
     doctor
    1.39
     airport
    1.39
     gym
    1.38
     grocery
    1.36
     mall
    1.35
     pharmacy
    1.27
    Activations Density 0.040%

    No Known Activations