© 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. 43351
    Prev
    Next
    INDEX
    Explanations

    Plato and his philosophy

    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
     expansions
    0.42
    ewidth
    0.41
    ទំន
    0.41
    Automation
    0.41
     automation
    0.41
    คองโก
    0.41
    ଇ
    0.41
    eksi
    0.41
    八
    0.40
    ោក
    0.40
    POSITIVE LOGITS
     Socrates
    0.76
     Plato
    0.75
     Athens
    0.70
    Athens
    0.68
     Athenian
    0.66
     Crete
    0.54
     chari
    0.50
     Athenians
    0.50
     교육
    0.49
     Sok
    0.48
    Activations Density 0.013%

    No Known Activations