© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49329
    Prev
    Next
    INDEX
    Explanations

    legal documents and entities

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

    The neuron activates on administrative or header metadata tokens—things like case captions, judge names, dates, bylines, version numbers, and similar document‐level header information.

    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
     directors
    -0.68
    factura
    -0.67
     distortions
    -0.66
    INTAIN
    -0.66
     Grover
    -0.66
     reverb
    -0.65
     pře
    -0.64
    getAttribute
    -0.64
    arar
    -0.63
     Distortion
    -0.62
    POSITIVE LOGITS
     userDetails
    0.70
    geist
    0.70
    unuz
    0.69
    opia
    0.68
     する
    0.68
    äck
    0.66
    mohonan
    0.66
    primaryColor
    0.65
     Creat
    0.64
    endis
    0.64
    Activations Density 0.076%

    No Known Activations