© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39140
    Prev
    Next
    INDEX
    Explanations

    electrolyzers, converters, esters, chlorine, Firefox

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

    scientific or technical terms used in research papers or academic contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on specialized, domain‐specific technical nouns (i.e. jargon terms you’d see in research titles or abstracts).

    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
    Woods
    -1.02
     juge
    -0.99
    аа
    -0.91
    钠
    -0.90
    Dough
    -0.85
    ARU
    -0.84
    АР
    -0.84
    бель
    -0.83
     traditionnelle
    -0.83
     cramps
    -0.82
    POSITIVE LOGITS
     or
    1.10
     variety
    0.87
    リエーション
    0.85
     ejercer
    0.81
     type
    0.79
     varieties
    0.79
     variants
    0.79
     variant
    0.77
    Isn
    0.76
     usarlo
    0.74
    Activations Density 0.168%

    No Known Activations