© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21992
    Prev
    Next
    INDEX
    Explanations

    domestic violence and abuse

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

    The neuron fires strongly on occurrences of the word “domestic,” especially in phrases like “domestic violence” or “domestic abuse.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    犼
    -2.56
     they
    -2.22
    yym
    -2.16
     houver
    -2.14
     Heilige
    -2.03
    
    -2.03
    </i>
    -2.00
     représente
    -2.00
     máte
    -1.99
     originalmente
    -1.98
    POSITIVE LOGITS
    1
    3.14
    m
    2.92
    d
    2.63
    9
    2.45
    4
    2.38
    6
    2.30
    However
    2.28
    what
    2.20
    f
    2.19
    and
    2.16
    Activations Density 0.004%

    No Known Activations