© 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. 33737
    Prev
    Next
    INDEX
    Explanations

    internship

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

    The main thing this neuron does is find mentions of internships or interns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ありますが
    -2.41
    🫃
    -2.36
     belangrij
    -2.36
    出て
    -2.34
    憷
    -2.27
    あります
    -2.25
     preparada
    -2.23
     jejich
    -2.16
    友好
    -2.16
     cercana
    -2.14
    POSITIVE LOGITS
    {
    2.91
    ),
    2.23
    ]
    2.08
    ization
    2.06
     zeitung
    2.03
    </strong>
    2.02
    what
    2.00
     sebagai
    2.00
     TWO
    1.99
    喬
    1.99
    Activations Density 0.003%

    No Known Activations