© 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. 67739
    Prev
    Next
    INDEX
    Explanations

    under followed by deficiency

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

    The neuron detects occurrences of the prefix “under” (e.g. in underfunded, underreported, underutilization, etc.).

    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
     diminutive
    -1.85
     сфере
    -1.84
    like
    -1.80
     by
    -1.75
     geringe
    -1.73
    and
    -1.67
    R
    -1.66
     naïve
    -1.65
     to
    -1.63
     for
    -1.59
    POSITIVE LOGITS
     confiable
    1.93
     duradero
    1.88
     plegable
    1.82
     carcasa
    1.79
    躝
    1.73
     assortment
    1.73
    嫪
    1.71
     prestaciones
    1.70
     intensively
    1.70
     assorted
    1.70
    Activations Density 0.014%

    No Known Activations