© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128147
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on semantically rich content words—especially topical nouns and technical terms—rather than on common function words.

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

    explaining effects or relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     můžete
    -0.88
    を購入
    -0.87
     artículos
    -0.87
     explicado
    -0.85
     棟
    -0.84
     řed
    -0.84
     ぽ
    -0.84
    ldre
    -0.83
     antiguos
    -0.82
     нравится
    -0.82
    POSITIVE LOGITS
     by
    1.02
     he
    0.93
     Meredith
    0.92
    }]);
    0.92
     helping
    0.85
    })();
    0.82
    小行星
    0.81
     through
    0.80
     helps
    0.80
     junio
    0.79
    Activations Density 0.126%

    No Known Activations