© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 64159
    Prev
    Next
    INDEX
    Explanations

    legal requirements and actions

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

    The neuron spotlights legal‐procedure language that says a party “must present sufficient facts to permit the court to reasonably conclude…”

    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
     quickly
    -1.02
     while
    -0.94
     just
    -0.94
    要不要
    -0.85
     may
    -0.85
     instantly
    -0.84
     keep
    -0.84
     when
    -0.82
     прекрасно
    -0.82
     very
    -0.81
    POSITIVE LOGITS
     suffisamment
    1.32
     kormány
    1.23
     sufficiently
    1.20
    sufficient
    1.17
    至少
    1.14
    才行
    1.05
     '(
    1.02
     konkre
    1.01
     "
    1.00
     alguna
    0.98
    Activations Density 0.015%

    No Known Activations