© 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. 10-GEMMASCOPE-RES-131K
    7. 101440
    Prev
    Next
    INDEX
    Explanations

    types of things

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

    The neuron fires strongly on central scientific topic words—especially field-specific, often plural, technical nouns naming key subjects or components of a study.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -2.31
     this
    -1.79
     "
    -1.66
    ロゴ
    -1.59
     такая
    -1.55
    柃
    -1.52
    部の
    -1.52
    许久
    -1.49
     its
    -1.48
    []=$
    -1.46
    POSITIVE LOGITS
     themselves
    2.61
     are
    2.38
     promesas
    2.17
    gorro
    1.92
     It
    1.91
     intervenciones
    1.91
    偸
    1.88
     actuaciones
    1.87
     negociaciones
    1.84
    嫱
    1.78
    Activations Density 0.170%

    No Known Activations