© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 60501
    Prev
    Next
    INDEX
    Explanations

    wrap my head around

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

    This neuron detects colloquial expressions of having difficulty understanding something (e.g. “wrapping my head around,” “hard time,” “grasping”).

    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
     you
    -1.55
     to
    -1.45
     dando
    -1.32
    !!!!!!!
    -1.28
    就可以了
    -1.27
    టు
    -1.22
    mesine
    -1.22
     vostre
    -1.20
     tasche
    -1.20
     jums
    -1.20
    POSITIVE LOGITS
     how
    1.83
     why
    1.70
     that
    1.34
     cumbersome
    1.29
    nological
    1.26
    )،
    1.26
     איך
    1.24
    rägen
    1.23
    eners
    1.22
    ionate
    1.22
    Activations Density 0.043%

    No Known Activations