© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116158
    Prev
    Next
    INDEX
    Explanations

    your, you, about, background

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

    This neuron detects job‐interview question phrases asking about a candidate’s qualities, skills, or reasons for being suited to a position.

    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
     sirop
    -1.48
     pietre
    -1.34
     przecież
    -1.33
     jari
    -1.32
     vinil
    -1.31
     paus
    -1.31
     colar
    -1.30
     bicic
    -1.30
     herbes
    -1.26
     conster
    -1.26
    POSITIVE LOGITS
     your
    3.05
     you
    2.50
     or
    1.79
     yourself
    1.72
     jste
    1.70
     vaše
    1.69
     Ihrer
    1.61
    </h2>
    1.51
     vaš
    1.45
     byste
    1.44
    Activations Density 0.018%

    No Known Activations