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
    3. 16-GEMMASCOPE-2-RES-16K
    4. 452
    Prev
    Next
    INDEX
    Explanations

    Springs at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ina
    0.55
    ja
    0.46
    ai
    0.43
    ona
    0.43
    na
    0.41
    ata
    0.40
    ali
    0.40
    á
    0.40
    os
    0.38
    lympi
    0.38
    POSITIVE LOGITS
     in
    0.50
    在
    0.49
     the
    0.48
     days
    0.44
     forcing
    0.40
     cars
    0.40
     legacies
    0.39
     water
    0.39
     foods
    0.39
     for
    0.38
    Activations Density 1.802%

    No Known Activations