© 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. 112667
    Prev
    Next
    INDEX
    Explanations

    names of people or companies

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

    The neuron is strongly triggered by capitalized proper nouns—names of people, organizations, and places.

    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
     oth
    -1.27
    vasion
    -1.22
    咬牙
    -1.19
     Illust
    -1.09
    }=\
    -1.08
     titled
    -1.08
    ts
    -1.06
     to
    -1.06
    となり
    -1.05
     "..\..\..\
    -1.05
    POSITIVE LOGITS
     what
    1.39
    vió
    1.38
     imidlertid
    1.30
     delicately
    1.30
     however
    1.29
     ifølge
    1.23
     staunch
    1.23
     különböző
    1.23
    osidad
    1.21
     ».
    1.20
    Activations Density 0.134%

    No Known Activations