© 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. 644
    Prev
    Next
    INDEX
    Explanations

    word beginnings

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

    word beginnings

    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
    ik
    0.75
     and
    0.74
    1
    0.64
    на
    0.63
    ಾ
    0.63
     has
    0.62
    の
    0.62
    im
    0.61
     or
    0.61
    н
    0.58
    POSITIVE LOGITS
    。
    0.48
     palpable
    0.46
     perceptible
    0.45
    ۔
    0.44
     flapping
    0.43
    0.42
    odynam
    0.41
     berkaitan
    0.40
    gue
    0.38
     distracting
    0.38
    Activations Density 0.304%

    No Known Activations