© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42022
    Prev
    Next
    INDEX
    Explanations

    explodes, blossoms, alive, free

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

    The neuron fires on verbs and verb-derived nouns that evoke rapid growth, expansion, or flourishing (e.g. “exploded,” “blossomed,” “flowered,” “coming alive”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     beslu
    -1.38
     grij
    -1.37
     sendiri
    -1.34
     spokoj
    -1.31
     óra
    -1.31
     ſou
    -1.30
     utiliser
    -1.30
     ImportError
    -1.30
     réus
    -1.27
     vriende
    -1.27
    POSITIVE LOGITS
     from
    1.85
     like
    1.52
     especially
    1.39
     with
    1.38
     as
    1.33
     August
    1.30
     through
    1.30
     July
    1.25
     January
    1.24
    などなど
    1.23
    Activations Density 0.059%

    No Known Activations