© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32964
    Prev
    Next
    INDEX
    Explanations

    society or Gesellschaft

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

    society for

    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
    Not in Any Lists

    No Comments

    Negative Logits
     коли
    0.52
    報酬
    0.50
     何
    0.49
    座標
    0.48
    同時
    0.46
    出
    0.46
     леген
    0.46
    }$}
    0.46
    態度
    0.45
     amikor
    0.45
    POSITIVE LOGITS
     Society
    0.86
     society
    0.84
    Society
    0.80
     societies
    0.77
     Societies
    0.76
     SOCIETY
    0.75
     sociedades
    0.68
     masyarakat
    0.68
    society
    0.68
     Gesellschaft
    0.64
    Activations Density 0.031%

    No Known Activations