© 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. 30784
    Prev
    Next
    INDEX
    Explanations

    legal documents and statements

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

    The neuron is picking out legal‐procedure terms and document references (e.g. affidavit, warrant, petition, file, document, notice).

    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
    壳
    -0.76
    霸王
    -0.74
    прос
    -0.73
    elif
    -0.72
     outputs
    -0.68
     output
    -0.68
    殼
    -0.66
    ẖ
    -0.66
    ಳ
    -0.66
    strs
    -0.66
    POSITIVE LOGITS
     affidavit
    3.14
     affidavits
    2.77
     sworn
    2.55
     Affidavit
    2.31
    Aff
    2.30
     swore
    2.25
     swearing
    2.08
    aff
    2.05
     aff
    1.98
     swears
    1.98
    Activations Density 0.027%

    No Known Activations