© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90407
    Prev
    Next
    INDEX
    Explanations

    qualify for

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

    The neuron selectively activates on the word “qualify” (and its inflected forms like “qualifies,” “qualifying,” “failed to qualify”) and its immediate context.

    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
    blurRadius
    -2.16
    
    -1.98
     and
    -1.93
    )」
    -1.93
    you
    -1.91
     habrá
    -1.84
    衪
    -1.83
     $
    -1.82
    ми
    -1.80
    情侣
    -1.80
    POSITIVE LOGITS
    媜
    2.16
    巔
    2.03
     chrétiens
    2.03
    CurtirCurtir
    1.98
    味道
    1.95
    ackerel
    1.95
     ส์
    1.92
    莖
    1.91
    不时
    1.88
     endereco
    1.86
    Activations Density 0.005%

    No Known Activations