© 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. 22-GEMMASCOPE-RES-131K
    7. 68158
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts

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

    This neuron fires strongly on the principal subject noun (the key technical/topic word) of a code or paper snippet.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     preſent
    -0.98
    Ār
    -0.97
     unſ
    -0.96
    Ꭴ
    -0.91
     fotbal
    -0.91
     คน
    -0.90
    AfterViewInit
    -0.90
     inteligen
    -0.90
     leſs
    -0.89
    During
    -0.88
    POSITIVE LOGITS
     quedará
    1.01
     itself
    1.00
     so
    0.97
     can
    0.92
     volverá
    0.92
    ATELY
    0.91
    ᧐
    0.90
     who
    0.89
     recibirá
    0.86
    Sprint
    0.84
    Activations Density 0.104%

    No Known Activations