© 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. 10961
    Prev
    Next
    INDEX
    Explanations

    benefits of having

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

    This neuron responds to abstract evaluation nouns (like “importance,” “benefits,” “supporting,” “implementation,” etc.) that signal pros/cons or explanatory discourse.

    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
     мужская
    -1.55
     męska
    -1.55
     all
    -1.53
     comenzará
    -1.52
     motocicletas
    -1.52
     tevreden
    -1.46
    さんも
    -1.45
     that
    -1.45
     hará
    -1.44
     zimowa
    -1.44
    POSITIVE LOGITS
     being
    2.39
     having
    1.84
    这种
    1.71
    being
    1.63
    having
    1.38
     knowing
    1.37
    他
    1.36
    ила
    1.33
     seeing
    1.32
    櫚
    1.32
    Activations Density 0.063%

    No Known Activations