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. 7999
    Prev
    Next
    INDEX
    Explanations

    Tana Jones/Tashkil/Taman/TensorFlow

    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
     timed
    -2.56
    timed
    -1.93
    Timed
    -1.75
    TIM
    -1.13
     timers
    -0.99
     timing
    -0.97
     Time
    -0.96
     TIM
    -0.96
     timer
    -0.93
    Timing
    -0.92
    POSITIVE LOGITS
     Lumia
    0.86
    倒是
    0.83
     Falk
    0.81
    providedIn
    0.78
     Categor
    0.78
    űr
    0.76
     Wishlist
    0.76
    travail
    0.76
     '',
    
    0.75
    erial
    0.75
    Activations Density 0.005%

    No Known Activations