© 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. 44229
    Prev
    Next
    INDEX
    Explanations

    severely impacted

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

    The neuron responds to the intensifier “severely,” flagging occurrences of that strong adverb.

    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
    嫆
    -2.77
    𐄁
    -2.50
    OUTUBE
    -2.38
    𓆏
    -2.25
     皇族
    -2.20
    GEBUR
    -2.20
    〠
    -2.20
    媖
    -2.20
     ſou
    -2.19
    
    -2.19
    POSITIVE LOGITS
    '
    3.91
    1
    2.56
    就是
    2.34
     "
    2.31
    re
    2.28
     zelfs
    2.17
     terwijl
    2.16
    </h2>
    2.11
     This
    2.06
    </h4>
    2.03
    Activations Density 0.006%

    No Known Activations