© 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. 91842
    Prev
    Next
    INDEX
    Explanations

    statement, hearsay, availability

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

    This neuron detects legal rule headings, i.e. section numbers followed by their official titles (e.g. “Rule 902 – Evidence That Is Self-Authenticating”).

    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
     vorge
    -0.79
    
    -0.77
    Macro
    -0.75
    
    -0.75
    Yun
    -0.74
    Napoli
    -0.73
    binom
    -0.73
    гы
    -0.73
    Lens
    -0.72
    boldmath
    -0.72
    POSITIVE LOGITS
     hearsay
    1.39
     statements
    1.18
     statement
    1.11
     declar
    1.06
     Unavailable
    1.05
    statement
    0.98
     unavailable
    0.97
     availability
    0.94
     dying
    0.92
     Availability
    0.91
    Activations Density 0.030%

    No Known Activations