© 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. 59591
    Prev
    Next
    INDEX
    Explanations

    code tokens followed by punctuation

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

    The neuron fires on occurrences of the specific module path “caliban.client.”

    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
    嗒
    -1.51
    囔
    -1.37
     elettrico
    -1.36
     this
    -1.23
     sportivo
    -1.21
    gemäß
    -1.18
     natale
    -1.18
     cucchia
    -1.16
     cucchiai
    -1.16
     \
    -1.15
    POSITIVE LOGITS
    ığın
    1.50
    íguez
    1.40
     también
    1.40
    ṝ
    1.40
     imágenes
    1.38
     dasarnya
    1.35
    árez
    1.34
    ではでは
    1.34
     Jerusalén
    1.33
     sorpresas
    1.33
    Activations Density 0.032%

    No Known Activations