© 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. 34-GEMMASCOPE-RES-131K
    7. 117312
    Prev
    Next
    INDEX
    Explanations

    great experience

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

    The neuron activates on the apostrophe character (i.e. occurrences of “’” in contractions or possessives).

    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
     зима
    -0.98
    enyum
    -0.97
    ЛИ
    -0.94
     исследования
    -0.94
     skuto
    -0.91
    tager
    -0.90
    iK
    -0.89
     juridique
    -0.88
    cire
    -0.88
     Configuración
    -0.88
    POSITIVE LOGITS
     this
    1.86
     great
    1.57
     excellent
    1.53
     очень
    1.39
     very
    1.34
    great
    1.22
     I
    1.18
     really
    1.17
     nice
    1.15
     Very
    1.13
    Activations Density 0.018%

    No Known Activations