© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8345
    Prev
    Next
    INDEX
    Explanations

    wild followed by common terms

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

    wild flowers and hunt

    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_40_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
    ennzeichnet
    0.48
    publique
    0.46
    奉
    0.45
    MyDB
    0.42
    ccncc
    0.42
     身
    0.40
    REEN
    0.39
     MAKE
    0.39
    ប់
    0.39
    bible
    0.38
    POSITIVE LOGITS
     wild
    1.35
     Wild
    1.17
    Wild
    1.14
    wild
    1.05
     WILD
    1.02
     wilde
    1.02
     wildcard
    0.93
    野
    0.88
     जंगली
    0.80
     wilds
    0.79
    Activations Density 0.058%

    No Known Activations