© 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. 54218
    Prev
    Next
    INDEX
    Explanations

    essence, travel, being

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

    The neuron fires on words that denote connecting or bridging between two places or entities.

    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
     signé
    -1.34
     startet
    -1.27
    颚
    -1.24
    مجموع
    -1.24
    ḿ
    -1.23
     emporter
    -1.21
     často
    -1.20
     poë
    -1.20
     mélanger
    -1.20
     célè
    -1.19
    POSITIVE LOGITS
     as
    1.63
     what
    1.62
     his
    1.62
     from
    1.49
     only
    1.38
     completely
    1.31
     created
    1.28
     even
    1.25
     by
    1.24
     being
    1.23
    Activations Density 0.022%

    No Known Activations