© 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. 79010
    Prev
    Next
    INDEX
    Explanations

    question/code delimiters

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

    The neuron is looking for HTML markup tokens (angle‐bracket tags and their attributes, especially form input fields).

    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
    estus
    -0.87
     triangulation
    -0.86
     Perfume
    -0.79
     перец
    -0.74
    ︻
    -0.73
     Lipstick
    -0.72
    PORTER
    -0.71
     modificar
    -0.71
     Fragrance
    -0.71
    راق
    -0.70
    POSITIVE LOGITS
     noise
    0.92
    干扰
    0.90
    噪
    0.83
    rilled
    0.79
     beach
    0.79
     noises
    0.76
     Kanada
    0.74
     Nag
    0.74
     SEE
    0.73
     slant
    0.71
    Activations Density 0.011%

    No Known Activations