© 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. 117574
    Prev
    Next
    INDEX
    Explanations

    pull right

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

    This neuron activates on HTML markup elements—i.e. tags and their structural attributes.

    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
     pierwszy
    -0.98
     kompetisi
    -0.93
     primeiro
    -0.88
     eerste
    -0.87
     primero
    -0.84
     primeira
    -0.83
    sieke
    -0.82
    klere
    -0.82
     below
    -0.80
    τυ
    -0.79
    POSITIVE LOGITS
     right
    2.28
    right
    1.80
    Right
    1.79
    右
    1.62
    pull
    1.62
     pull
    1.61
     Right
    1.58
     pulling
    1.52
    RIGHT
    1.47
     RIGHT
    1.43
    Activations Density 0.014%

    No Known Activations