© 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. 105906
    Prev
    Next
    INDEX
    Explanations

    Hamas or mammograms

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

    The neuron activates on HTML bold/emphasis tags (e.g. `<strong>` and `<b>`).

    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
    '
    -3.38
    ",
    -2.64
    }
    -2.47
    骉
    -2.30
    碌
    -2.30
     efectivos
    -2.23
    袂
    -2.20
     tlie
    -2.20
    ',
    -2.19
     команда
    -2.17
    POSITIVE LOGITS
    </strong>
    4.28
    8
    3.22
    <em>
    3.03
    6
    3.00
    7
    2.80
    What
    2.77
    EL
    2.72
    5
    2.69
    4
    2.64
    IN
    2.63
    Activations Density 0.001%

    No Known Activations