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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8138
    Prev
    Next
    INDEX
    Explanations

    hate speech

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

    The neuron strongly activates on words naming head coverings (e.g., hat, hood, cap).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     পর্বে
    0.59
    ితే
    0.57
    цкі
    0.57
     warmer
    0.55
    物质
    0.55
    따
    0.55
    warm
    0.55
     тепло
    0.55
    垍
    0.53
    ѳ
    0.53
    POSITIVE LOGITS
     HOT
    0.59
     Vez
    0.59
     Hat
    0.58
    クトル
    0.57
    chet
    0.56
     Hot
    0.54
     Objects
    0.53
     CHECK
    0.52
     hivyo
    0.52
    ),]),
    0.52
    Activations Density 0.193%

    No Known Activations