© 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. 65297
    Prev
    Next
    INDEX
    Explanations

    major or principal followed by noun

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

    This neuron spotlights words that denote key importance or prominence (e.g. “principal,” “major,” “primary”).

    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
     a
    -2.48
    kamer
    -1.75
     essas
    -1.70
    borsa
    -1.67
    嫌疑
    -1.63
    Trichlor
    -1.61
     on
    -1.56
     bandits
    -1.52
     normalmente
    -1.51
     instead
    -1.50
    POSITIVE LOGITS
    ^^;
    1.77
     two
    1.68
     nostru
    1.63
    };
    1.51
    <bos>
    1.50
    ↵
    1.48
     costuras
    1.44
    几个
    1.40
     sombrero
    1.39
    無料で
    1.38
    Activations Density 0.051%

    No Known Activations