© 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. 34-GEMMASCOPE-RES-131K
    7. 69828
    Prev
    Next
    INDEX
    Explanations

    or agreed

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

    This neuron detects the legal‐license boilerplate, especially the “unless required by applicable law or agreed to in writing” disclaimer phrasing.

    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
    延迟
    -0.70
    reliance
    -0.68
    gee
    -0.68
     Cuad
    -0.68
     שול
    -0.67
    支部
    -0.66
    umbar
    -0.66
     oppervlak
    -0.65
    ρούν
    -0.65
    naw
    -0.65
    POSITIVE LOGITS
    ]];
    0.76
    ❻
    0.73
    CAL
    0.69
     リ
    0.68
     CAL
    0.68
    istiques
    0.68
    (!__
    0.67
     حرف
    0.66
     rellen
    0.65
    DataRow
    0.65
    Activations Density 0.060%

    No Known Activations