© 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. 31-GEMMASCOPE-2-RES-262K
    7. 17079
    Prev
    Next
    INDEX
    Explanations

    specialises in physiological description

    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_31_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
    í
    0.46
    大家都
    0.45
    ím
    0.42
     റാ
    0.40
    大家
    0.40
    ano
    0.39
    二
    0.39
    Ⲧ
    0.39
     чтобы
    0.39
    Không
    0.38
    POSITIVE LOGITS
     physiology
    0.44
     wellbeing
    0.42
     syrup
    0.40
     যদি
    0.39
     within
    0.39
     włas
    0.38
     Physiology
    0.38
     specialises
    0.38
     fusión
    0.38
     Physik
    0.37
    Activations Density 0.009%

    No Known Activations