© 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. 16-GEMMASCOPE-2-RES-65K
    7. 560
    Prev
    Next
    INDEX
    Explanations

    professional roles and experience levels

    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_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
     was
    0.64
     is
    0.55
    "
    0.53
    of
    0.50
    '
    0.49
     було
    0.46
     of
    0.46
    た
    0.46
     Dla
    0.45
     moeder
    0.45
    POSITIVE LOGITS
    x
    0.74
    w
    0.68
    ad
    0.67
    ol
    0.64
    ir
    0.62
    r
    0.61
    é
    0.60
    ə
    0.57
    ill
    0.55
    f
    0.53
    Activations Density 0.498%

    No Known Activations