© 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. 57739
    Prev
    Next
    INDEX
    Explanations

    legal representation and case handling

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

    The neuron flags passages that mention attorneys, law firms, or legal representation.

    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
    ichtigung
    -0.87
    曬
    -0.84
    magini
    -0.82
    빚
    -0.81
     WARRANT
    -0.79
    czer
    -0.78
    ൃ
    -0.76
     OpenAPI
    -0.75
    зади
    -0.75
     axial
    -0.74
    POSITIVE LOGITS
     representation
    3.41
     represent
    3.03
     representing
    2.98
    representation
    2.81
    Represent
    2.80
    Representation
    2.80
     handling
    2.70
     represents
    2.61
     Representation
    2.59
     representations
    2.58
    Activations Density 0.057%

    No Known Activations