© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 3721
    Prev
    Next
    INDEX
    Explanations

    quality and control

    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
     
    1.05
    ’
    0.99
     ошибка
    0.81
    जानिए
    0.81
     sıvı
    0.80
     titik
    0.80
     macchina
    0.80
     imprend
    0.80
     acqua
    0.79
     endroit
    0.79
    POSITIVE LOGITS
    it
    1.77
    u
    1.74
    us
    1.69
    p
    1.57
    ad
    1.54
    ol
    1.53
    y
    1.50
    on
    1.45
    al
    1.45
    ing
    1.44
    Activations Density 0.041%

    No Known Activations