© 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. 13740
    Prev
    Next
    INDEX
    Explanations

    entities

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

    The neuron responds strongly to capitalized entity names or identifiers (e.g. class names, model names, file or resource names, proper nouns) in code or text.

    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
    をご紹介
    -1.41
    飲んで
    -1.27
    のご紹介
    -1.27
     necessarie
    -1.26
     counted
    -1.19
    Legenda
    -1.13
     olvidado
    -1.13
     perder
    -1.12
     recic
    -1.11
    irim
    -1.10
    POSITIVE LOGITS
    to
    1.32
    IC
    1.23
    UR
    1.21
    OS
    1.20
    data
    1.17
    SC
    1.16
     sämtliche
    1.15
    诋
    1.13
    CC
    1.13
    SP
    1.12
    Activations Density 0.048%

    No Known Activations