© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 884
    Prev
    Next
    INDEX
    Explanations

    if we

    np_acts-logits-general · gemini-2.5-flash-lite

    initiating conditional phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    0.72
     of
    0.68
     I
    0.64
     is
    0.60
     was
    0.59
    จะ
    0.59
    ные
    0.58
    เป็น
    0.54
    는
    0.54
    </h1>
    0.52
    POSITIVE LOGITS
    t
    0.69
    써
    0.64
    IN
    0.56
    MJ
    0.56
    𝙜
    0.56
     SoaException
    0.55
    𝙝
    0.55
    the
    0.54
    H
    0.54
    capitalize
    0.54
    Activations Density 0.729%

    No Known Activations