© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93480
    Prev
    Next
    INDEX
    Explanations

    handled responsibilities

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

    The neuron strongly activates on the third-person masculine pronoun “he.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    活動を
    -0.84
    tando
    -0.82
     megjelen
    -0.81
     esetben
    -0.81
    voc
    -0.81
    ucus
    -0.79
    Wings
    -0.78
    Founder
    -0.78
     featuring
    -0.78
    }
    -0.77
    POSITIVE LOGITS
     responsible
    1.93
     handling
    1.70
    负责
    1.61
     responsibility
    1.55
     respon
    1.53
     handle
    1.48
     overseeing
    1.44
    Responsible
    1.41
     oversee
    1.41
     help
    1.38
    Activations Density 0.058%

    No Known Activations