© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7950
    Prev
    Next
    INDEX
    Explanations

    quoted words or phrases

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

    This neuron detects words (or short phrases) enclosed in quotation marks.

    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
    曾经
    -1.26
    曾經
    -1.26
    คือ
    -1.26
     micrófono
    -1.25
    終於
    -1.22
    經常
    -1.13
    现在
    -1.12
     validar
    -1.10
    现在的
    -1.09
     beleid
    -1.09
    POSITIVE LOGITS
     out
    1.55
     also
    1.52
     help
    1.23
     
    1.23
    うま
    1.22
     later
    1.20
    也算是
    1.20
     first
    1.17
    bhan
    1.16
     day
    1.15
    Activations Density 0.049%

    No Known Activations