© 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. 34-GEMMASCOPE-RES-131K
    7. 58623
    Prev
    Next
    INDEX
    Explanations

    job interviews and offers

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

    This neuron fires on personal narrative career-advice posts, spotting first-person (and sometimes second-person) descriptions of job offers, applications, and related numeric details.

    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
     mengumumkan
    -0.99
    цыі
    -0.98
    imbangan
    -0.90
    あなたが
    -0.87
     světě
    -0.86
    כשיו
    -0.86
    öhnen
    -0.85
     mls
    -0.84
     работают
    -0.83
    従来
    -0.83
    POSITIVE LOGITS
     interview
    1.55
     interviewing
    1.26
     entrevista
    1.26
    Interview
    1.23
     panel
    1.20
     Interview
    1.20
    interview
    1.20
     interviews
    1.16
     was
    1.14
     recruiter
    1.13
    Activations Density 0.019%

    No Known Activations