© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70388
    Prev
    Next
    INDEX
    Explanations

    neglect or neglected

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

    The neuron detects mentions of “neglect” (in all its inflected or compound forms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ar
    -2.39
    PopMatrix
    -2.38
    鼉
    -2.27
    derdag
    -2.16
     }));
    -2.11
    ⼼
    -2.09
    優惠
    -2.09
     })}
    -2.09
    Ꮣ
    -2.03
     منع
    -2.00
    POSITIVE LOGITS
    ↵
    4.06
     of
    2.97
     I
    2.38
    larını
    2.06
     but
    2.03
     treacherous
    1.98
     pudieron
    1.91
     podían
    1.91
     also
    1.84
    giaan
    1.84
    Activations Density 0.007%

    No Known Activations