© 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. 221742
    Prev
    Next
    INDEX
    Explanations

    aggregating into, continue growing

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

    dehumanization and negative stereotypes

    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
     (%)
    0.50
     VIII
    0.50
     Module
    0.49
     darker
    0.49
     pandas
    0.48
     popul
    0.47
     c
    0.46
     script
    0.46
     kg
    0.46
     premiere
    0.46
    POSITIVE LOGITS
     watertight
    0.48
    żu
    0.47
    errick
    0.46
    довать
    0.46
    お手
    0.45
    footnotesize
    0.45
    ουν
    0.44
     ውስ
    0.44
    boden
    0.44
    稒
    0.44
    Activations Density 0.000%

    No Known Activations