© 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. 13730
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and metaphors

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

    The neuron fires strongly on vivid, concrete imagery words used in analogies or promotional metaphors—e.g. “symphony,” “sound,” “fire,” “burning,” “beautiful.”

    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
    ֶּ
    -1.11
    ְּ
    -1.04
    ּוֹ
    -1.03
    ִּ
    -0.98
    tilus
    -0.92
    וּ
    -0.88
    кож
    -0.86
    ַּ
    -0.86
     الكم
    -0.86
     общения
    -0.84
    POSITIVE LOGITS
     metaphorical
    1.20
     to
    1.08
     our
    1.05
    ׇ
    1.02
     metaphor
    1.02
    ⑅
    0.96
     your
    0.90
     analogy
    0.90
    学年
    0.89
    Boxscore
    0.88
    Activations Density 0.042%

    No Known Activations