© 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. 95495
    Prev
    Next
    INDEX
    Explanations

    section headers and metadata

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

    The neuron spikes on the “http” token, i.e. it detects the start of a web‐link or URL.

    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
     lavabo
    -1.15
     europ
    -1.09
     tenis
    -1.04
     turista
    -1.02
    mapStateToProps
    -1.02
     fases
    -1.02
     THAN
    -0.99
    ittää
    -0.98
     ModelRenderer
    -0.97
     ③
    -0.94
    POSITIVE LOGITS
     húmedo
    1.02
    會有
    0.97
     шесть
    0.96
     erwäh
    0.96
     病院
    0.95
     effetto
    0.95
     présentes
    0.94
     takiego
    0.94
    BB
    0.93
     warto
    0.93
    Activations Density 0.008%

    No Known Activations