© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6726
    Prev
    Next
    INDEX
    Explanations

    not prior art

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

    The neuron flags patent‐style boilerplate disclaiming that a section “is not prior art,” i.e. the negation “not” in those boilerplate statements.

    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
     Nature
    -0.72
    勵
    -0.70
     from
    -0.70
     Rox
    -0.69
     at
    -0.68
    ampung
    -0.68
    
    -0.68
     Фа
    -0.67
     long
    -0.66
     Фе
    -0.66
    POSITIVE LOGITS
    metto
    0.90
    llt
    0.89
     interactiva
    0.86
    Preparation
    0.84
    Lb
    0.83
     nervousness
    0.83
     ativo
    0.81
     confortable
    0.81
    ternut
    0.79
    浜
    0.79
    Activations Density 0.007%

    No Known Activations