© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47937
    Prev
    Next
    INDEX
    Explanations

    going after or targeting

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

    The neuron fires on words that denote pursuing, attacking, or targeting someone or something.

    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
    一個
    -1.48
    were
    -1.34
     and
    -1.30
    💗
    -1.30
    賈
    -1.29
    If
    -1.28
    It
    -1.28
    😻
    -1.27
     gese
    -1.25
    😘
    -1.21
    POSITIVE LOGITS
     to
    1.53
    szt
    1.40
    งิน
    1.38
    着他
    1.30
     /$
    1.29
    なども
    1.28
    蟜
    1.28
    鳎
    1.24
    だけでなく
    1.24
     him
    1.23
    Activations Density 0.039%

    No Known Activations