© 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. 70560
    Prev
    Next
    INDEX
    Explanations

    qualified and qualification

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

    The neuron detects occurrences of “qualify” and its derivatives—words about qualification or credentialing.

    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
     You
    -2.42
     $
    -2.16
     ktorí
    -1.95
    櫺
    -1.94
    nyv
    -1.90
    푘
    -1.88
     afectadas
    -1.84
    鬭
    -1.82
     belieb
    -1.80
    ᨗ
    -1.80
    POSITIVE LOGITS
    0
    2.19
    .”
    2.19
    ’
    2.16
    up
    2.11
    峮
    2.05
    кову
    1.98
    .
    1.84
     الرئيسي
    1.77
    </sup>
    1.76
    而又
    1.74
    Activations Density 0.010%

    No Known Activations