© 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. 92668
    Prev
    Next
    INDEX
    Explanations

    clone

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

    The neuron strongly activates on occurrences of “clone” and its morphological variants (cloned, cloning, cloneable, super.clone, etc.).

    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
     petitioners
    -0.82
     carcin
    -0.79
     वाल
    -0.79
    ξεις
    -0.77
     Collaboration
    -0.73
     interrogation
    -0.71
     referee
    -0.71
    ramento
    -0.69
    Collaboration
    -0.69
     Hing
    -0.69
    POSITIVE LOGITS
     clone
    2.86
     cloning
    2.73
     Clone
    2.66
    clone
    2.52
    Clone
    2.48
     cloned
    2.44
     clones
    2.36
     Cloning
    2.06
    cloned
    1.98
     clon
    1.90
    Activations Density 0.047%

    No Known Activations