© 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. 85434
    Prev
    Next
    INDEX
    Explanations

    held positions or jobs

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

    the past-tense verb “held” indicating someone occupied or served in 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_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
     brillant
    -1.48
    ឣ
    -1.39
     literalmente
    -1.38
     about
    -1.37
    もしっかり
    -1.31
     ของ
    -1.31
     Natürlich
    -1.29
     inicialmente
    -1.28
     of
    -1.27
     coiff
    -1.27
    POSITIVE LOGITS
     positions
    1.59
     jobs
    1.59
    ing
    1.58
     job
    1.53
     other
    1.52
    Jobs
    1.43
    ’
    1.41
    Positions
    1.34
    g
    1.28
    is
    1.27
    Activations Density 0.060%

    No Known Activations