© 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. 104746
    Prev
    Next
    INDEX
    Explanations

    links to http or https

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

    the opening quotation mark in HTML href attributes.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron responds to numeric tokens (sequences of digits) in the text, such as standalone numbers or numbers within URLs/IDs.

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

    HTML anchor hyperlinks, focusing on the href attribute and embedded URLs.

    oai_token-act-pair · gpt-5Triggered 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
     späteren
    -1.60
    jenigen
    -1.60
     conseguiu
    -1.47
    </b>
    -1.47
     retrô
    -1.46
    诶
    -1.46
    </sup>
    -1.43
     décédé
    -1.41
     usadas
    -1.40
    SenderId
    -1.40
    POSITIVE LOGITS
    嗵
    1.63
    СЫ
    1.63
    😛
    1.60
    скать
    1.59
     and
    1.56
    逦
    1.54
    ﻂ
    1.51
    нік
    1.50
    all
    1.48
     montana
    1.48
    Activations Density 0.007%

    No Known Activations