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-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 14066
    Prev
    Next
    INDEX
    Explanations

    used to introduce a definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     («
    0.78
     („
    0.69
     ("
    0.68
     ('
    0.64
     (‘
    0.64
     (“
    0.55
     (\"
    0.51
     ("[
    0.47
     designating
    0.46
     (`
    0.46
    POSITIVE LOGITS
     called
    1.44
    called
    1.27
     Called
    1.13
     llamado
    1.06
    Called
    1.04
     chamado
    1.04
     कॉल्ड
    0.99
    叫
    0.97
     llamados
    0.95
     appelé
    0.95
    Activations Density 0.055%

    No Known Activations