© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14123
    Prev
    Next
    INDEX
    Explanations

    introduction

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

    The neuron fires on site- or document-level metadata and markup (e.g. front-matter fields and admin notices) rather than normal prose.

    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
     of
    -1.26
    EventData
    -1.16
     链
    -1.13
     baca
    -1.05
    ELTS
    -1.04
    મા
    -1.04
     Dijo
    -1.03
    langsung
    -1.02
     Características
    -1.01
     Février
    -1.01
    POSITIVE LOGITS
     toate
    1.07
     lentejuelas
    1.05
    不在
    1.04
     görüntüsü
    1.03
     gewal
    1.02
     empfiehlt
    1.00
    𓐍
    0.96
     lateinit
    0.95
     schreibt
    0.93
     escote
    0.93
    Activations Density 0.003%

    No Known Activations