© 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. 31-GEMMASCOPE-2-RES-262K
    7. 85219
    Prev
    Next
    INDEX
    Explanations

    hotel review score

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

    AI users and conversation topics

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     அனு
    0.53
     அனுப்ப
    0.52
    ıdır
    0.49
     杨
    0.49
    getMinutes
    0.47
     Dato
    0.47
    ැ
    0.46
     டன்
    0.46
     famously
    0.45
    éget
    0.45
    POSITIVE LOGITS
    劇場
    0.44
     doenças
    0.44
     contagion
    0.42
    ्रीन
    0.41
     wisata
    0.41
     varic
    0.40
    今後の
    0.39
    鬢
    0.39
    หล
    0.38
    -
    0.38
    Activations Density 0.000%

    No Known Activations