© 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. 10-GEMMASCOPE-RES-131K
    7. 41330
    Prev
    Next
    INDEX
    Explanations

    block actions

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

    The neuron strongly activates on occurrences of the word “block” (and its forms like “blocked” or “blocking”).

    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
    ☆☆☆
    -1.98
     土産
    -1.94
    The
    -1.91
    䨻
    -1.84
    攪
    -1.83
    ,
    -1.78
    ischof
    -1.69
    jewództ
    -1.67
    ⇘
    -1.66
    вий
    -1.65
    POSITIVE LOGITS
    ];
    2.97
    ೢ
    2.55
    );
    2.22
    耵
    2.16
    istischen
    1.95
    })
    1.94
     efectivos
    1.89
    ";
    1.88
    鯪
    1.88
    );
    1.86
    Activations Density 0.028%

    No Known Activations