© 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. 61165
    Prev
    Next
    INDEX
    Explanations

    associated with diagnostic

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

    The neuron detects instances of “used” (especially in passive or purpose constructions like “be used for,” “are used to,” “used to”) indicating described usage or function.

    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
    however
    -1.63
    d
    -1.60
    .”
    -1.55
    in
    -1.54
    but
    -1.52
    although
    -1.52
    You
    -1.45
        
    -1.45
    quelize
    -1.42
     avendo
    -1.41
    POSITIVE LOGITS
     --
    1.45
    }
    1.45
     empêche
    1.30
    SaveChangesAsync
    1.30
     \&
    1.27
     Beide
    1.27
     Não
    1.24
    önster
    1.23
    vgili
    1.23
     dialami
    1.22
    Activations Density 0.481%

    No Known Activations