© 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. 192465
    Prev
    Next
    INDEX
    Explanations

    rights or Athens

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

    emotional intimacy

    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
     ሽፋን
    0.54
     Besoin
    0.53
    LOTRE
    0.50
     كلم
    0.49
     इजी
    0.48
     اهم
    0.48
    甛
    0.48
     Loving
    0.48
    comics
    0.48
     Timurtaş
    0.48
    POSITIVE LOGITS
     may
    0.53
    ↵
    0.52
    芝
    0.51
    冥
    0.47
     sau
    0.45
     pair
    0.44
    ”
    0.43
     manner
    0.42
     adversaries
    0.42
    己
    0.42
    Activations Density 0.012%

    No Known Activations