© 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. 14674
    Prev
    Next
    INDEX
    Explanations

    ability to do things

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

    The neuron is triggered by words referring to someone’s ability, capability, or level of competence.

    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
     maniere
    -1.65
    耵
    -1.64
    ÍSTICAS
    -1.64
    茕
    -1.63
     œufs
    -1.62
     ſame
    -1.58
    蟊
    -1.58
     rigide
    -1.58
    黉
    -1.57
     salaire
    -1.56
    POSITIVE LOGITS
     and
    1.94
    1
    1.84
    s
    1.79
     see
    1.71
     what
    1.69
     by
    1.68
     
    1.61
     know
    1.59
     make
    1.45
     appropriate
    1.44
    Activations Density 0.017%

    No Known Activations