© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 120070
    Prev
    Next
    INDEX
    Explanations

    Forms, UI, Fluid development

    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_16_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
    ↵
    0.73
     spices
    0.66
     by
    0.62
     driving
    0.61
     Consequences
    0.59
     Globally
    0.59
     Driving
    0.59
     inputs
    0.58
     f
    0.55
     consequences
    0.55
    POSITIVE LOGITS
    ні
    0.64
    elijke
    0.61
    érrez
    0.59
    ették
    0.59
    écran
    0.57
    áreas
    0.57
    á
    0.57
    ześ
    0.56
    ła
    0.55
    еру
    0.54
    Activations Density 0.000%

    No Known Activations