© 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. 232539
    Prev
    Next
    INDEX
    Explanations

    resort location, started playing, entered into

    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
     provocar
    0.54
    зву
    0.53
    س
    0.52
     obiettivo
    0.49
     cominci
    0.49
     evidentemente
    0.49
     quartier
    0.49
    償
    0.49
    ⵡ
    0.49
    є
    0.48
    POSITIVE LOGITS
     choir
    0.46
    唱歌
    0.46
    ack
    0.46
    acés
    0.44
     áo
    0.43
     gro
    0.43
     Gro
    0.42
     Eagle
    0.42
    ád
    0.41
    ul
    0.41
    Activations Density 0.001%

    No Known Activations