© 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. 84819
    Prev
    Next
    INDEX
    Explanations

    opinions expressed are mine

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

    This neuron detects disclaimer language—phrases that qualify or distance the author’s opinions or content (e.g. “the thoughts and opinions expressed are those of the writer and not necessarily those of…”).

    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
    vori
    -0.93
     mention
    -0.88
    :
    -0.85
     for
    -0.84
    UINTN
    -0.82
     mentions
    -0.81
     to
    -0.79
     part
    -0.77
     portions
    -0.77
     names
    -0.76
    POSITIVE LOGITS
    expressed
    1.21
    sole
    1.13
     henkil
    1.12
     solely
    1.10
     those
    1.07
     исключительно
    1.02
    alone
    1.00
     expressed
    0.98
     riêng
    0.98
     eivät
    0.96
    Activations Density 0.028%

    No Known Activations