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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 52467
    Prev
    Next
    INDEX
    Explanations

    often appears

    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
    筱
    0.48
     ی
    0.43
     clockRadius
    0.43
    ردن
    0.42
     azonban
    0.42
     milliamperes
    0.42
     galactose
    0.41
     নাগ
    0.41
    খালী
    0.41
     createArticle
    0.41
    POSITIVE LOGITS
     Brexit
    0.51
     Putin
    0.49
    ’
    0.49
    assert
    0.46
     दुनिया
    0.44
     succès
    0.44
    $"
    0.43
     Africa
    0.42
    ua
    0.42
    els
    0.42
    Activations Density 0.012%

    No Known Activations