© 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. 130969
    Prev
    Next
    INDEX
    Explanations

    categories of services or entities

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

    The neuron spotlights salient content nouns—especially in compound terms or section titles—highlighting the main topical or proper‐name words in a passage.

    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
     that
    -2.05
    }();
    -1.83
    ."/
    -1.68
    }());
    -1.47
    //});
    -1.46
    ():
    -1.42
    atação
    -1.42
    tling
    -1.38
     actrice
    -1.37
    .='
    -1.37
    POSITIVE LOGITS
    鱟
    1.48
     erad
    1.23
     歯
    1.20
     spearheaded
    1.20
     the
    1.18
    gorra
    1.18
     seiz
    1.17
     disciplined
    1.16
    イエロー
    1.16
     vijf
    1.16
    Activations Density 3.747%

    No Known Activations