© 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. 65761
    Prev
    Next
    INDEX
    Explanations

    in a statement or announcement

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

    The neuron activates on the common “reporter‐attribution” sequence—tokens like said, in, a, statement—that occur in phrases such as “said in a statement.”

    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
    several
    -0.88
     что
    -0.87
     extremely
    -0.84
     expresar
    -0.84
    一些
    -0.82
    warded
    -0.82
    some
    -0.79
     another
    -0.79
    someone
    -0.79
     somewhat
    -0.78
    POSITIVE LOGITS
     a
    3.63
     statement
    0.95
     chistes
    0.86
     comunicado
    0.83
     tilby
    0.82
    樗
    0.81
     ønsker
    0.81
    Statement
    0.81
     release
    0.81
    鲱
    0.80
    Activations Density 0.024%

    No Known Activations