© 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. 34-GEMMASCOPE-RES-131K
    7. 47752
    Prev
    Next
    INDEX
    Explanations

    respondent or respondents

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

    The neuron responds to the repetitive function words and punctuation (especially commas) that appear in legal case captions and boilerplate metadata.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    }$​
    -0.95
    paroles
    -0.85
     sampah
    -0.78
    asgi
    -0.76
    вающая
    -0.74
    casque
    -0.74
     efficiency
    -0.71
    ŚĆ
    -0.71
    subtype
    -0.70
    teria
    -0.70
    POSITIVE LOGITS
     respondent
    1.57
     respondents
    1.38
     Respondents
    1.30
     Respondent
    1.25
    Respondent
    1.13
     Respond
    1.05
    respond
    1.05
     respond
    1.01
    Respondents
    1.00
    second
    0.93
    Activations Density 0.040%

    No Known Activations