© 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. 10-GEMMASCOPE-RES-131K
    7. 8186
    Prev
    Next
    INDEX
    Explanations

    text within quotation marks

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

    The neuron strongly activates on double-quote characters marking quoted titles or phrases in the text.

    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
    -1.91
    0
    -1.60
    s
    -1.38
    c
    -1.35
    若い
    -1.33
    8
    -1.32
    6
    -1.31
    d
    -1.30
    3
    -1.30
    我が家の
    -1.30
    POSITIVE LOGITS
    ‗
    1.86
    分に
    1.85
    ྜ
    1.70
    )$,
    1.70
     отредактировал
    1.66
     &=&
    1.62
     determinados
    1.62
    蠵
    1.61
    hooting
    1.56
     合金
    1.56
    Activations Density 0.056%

    No Known Activations