© 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. 22-GEMMASCOPE-RES-131K
    7. 129150
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on mentions of graduating or being a graduate.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    academic graduation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    en
    -2.58
     kteří
    -2.27
            
    -2.25
    ⟝
    -2.22
    ard
    -2.16
    でお
    -2.14
    }$
    -2.13
    訁
    -2.13
    所有人都
    -2.13
     peuvent
    -2.11
    POSITIVE LOGITS
    In
    2.59
     técn
    2.55
     of
    2.55
     手绘
    2.50
    Ꮸ
    2.45
     cromado
    2.34
     camiset
    2.31
     剧照
    2.31
     soixante
    2.30
     pozo
    2.28
    Activations Density 0.010%

    No Known Activations