© 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. 10-GEMMASCOPE-RES-131K
    7. 87069
    Prev
    Next
    INDEX
    Explanations

    galactic contexts

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

    The neuron activates on descriptive adjectives modifying nouns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    adjectival modifiers used before nouns, especially scientific-sounding (-ic/-ian) and hyphenated or -ed descriptive forms.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "Galactic" or "galactic" in science fiction and astronomy contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    鬭
    -2.50
    何度も
    -2.27
     decoradas
    -2.16
     themſelves
    -2.16
    檍
    -2.14
    ～。
    -2.09
     sweter
    -2.08
    Ꮸ
    -2.08
    鱨
    -2.08
     古风
    -2.05
    POSITIVE LOGITS
    $
    2.64
    ,"
    2.56
    ,.
    2.53
    л
    2.52
    </i>
    2.52
    瓩
    2.45
     to
    2.44
     .
    2.34
    家伙
    2.34
    ?.
    2.28
    Activations Density 0.002%

    No Known Activations