© 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. 34-GEMMASCOPE-RES-131K
    7. 1626
    Prev
    Next
    INDEX
    Explanations

    Pet or petal

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

    The neuron flags tokens that contain uppercase letters or digits (e.g. proper‐name parts and numbers).

    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
    livé
    -0.76
    教练
    -0.76
     sabi
    -0.75
     serius
    -0.75
     Whittaker
    -0.73
    דור
    -0.72
     cupola
    -0.71
    രു
    -0.71
     memang
    -0.70
     Meny
    -0.70
    POSITIVE LOGITS
     cuenta
    0.81
    ʼn
    0.81
    ungguhnya
    0.77
    펫
    0.74
     Nachhaltigkeit
    0.74
    EAST
    0.72
     consolid
    0.72
     lok
    0.71
    равда
    0.71
    Pet
    0.71
    Activations Density 0.027%

    No Known Activations