© 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. 22-GEMMASCOPE-RES-131K
    7. 39652
    Prev
    Next
    INDEX
    Explanations

    HTML line break

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

    The neuron is detecting HTML line-break tags (e.g. `<br>`).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     of
    -0.92
    Thus
    -0.90
     kony
    -0.87
     Therefore
    -0.87
    )}
    -0.85
     klinik
    -0.84
    」（
    -0.83
    »).
    -0.82
     kurie
    -0.81
     conseille
    -0.81
    POSITIVE LOGITS
     rispetto
    0.90
     secondly
    0.88
    istema
    0.85
     followed
    0.85
     boobs
    0.80
     Gewalt
    0.80
    会不会
    0.80
    Ethylbenzene
    0.79
     aussitôt
    0.79
    anhão
    0.79
    Activations Density 0.051%

    No Known Activations