© 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-65K
    7. 49238
    Prev
    Next
    INDEX
    Explanations

    describing or explaining concepts

    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_65k_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
    校
    0.43
     CEOs
    0.41
     Male
    0.41
    cari
    0.40
     regexp
    0.40
     profitability
    0.39
     igualdad
    0.39
     TEX
    0.39
    लेरिया
    0.39
     mejora
    0.38
    POSITIVE LOGITS
    uigen
    0.55
     നമു
    0.52
    酝
    0.50
     अध्या
    0.49
     നമ്മുടെ
    0.49
    .].
    0.49
    pathy
    0.48
     nostra
    0.48
    আমরা
    0.48
     ನಮ್ಮ
    0.48
    Activations Density 0.012%

    No Known Activations