© 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. 1393
    Prev
    Next
    INDEX
    Explanations

    body composition and functions

    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
     премии
    0.80
     Invitational
    0.79
     współpracy
    0.76
    FlaskApp
    0.75
     evaluación
    0.74
    鸰
    0.70
    ಕ್ಸ್
    0.69
    фессиона
    0.68
    ствовал
    0.68
    িমূলক
    0.68
    POSITIVE LOGITS
     cells
    0.94
     muscles
    0.83
    _
    0.79
     walls
    0.79
     fleshy
    0.79
     proteins
    0.75
     arteries
    0.75
     cell
    0.73
     structure
    0.73
     tissues
    0.73
    Activations Density 0.620%

    No Known Activations