© 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. 30818
    Prev
    Next
    INDEX
    Explanations

    orbital perigee or perihelion

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

    The neuron is highly sensitive to the scientific term “perihelion” (often split across tokens like per-, ihe-, lion) wherever it appears.

    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
    naam
    -0.79
    ].)
    -0.78
    >>(
    -0.77
    posedge
    -0.75
     rowspan
    -0.74
    rain
    -0.69
    GetEnumerator
    -0.69
    钻
    -0.68
     стек
    -0.68
    liza
    -0.68
    POSITIVE LOGITS
     closest
    1.45
    closest
    1.15
     approaches
    1.02
     approached
    0.91
    Closest
    0.88
     passagem
    0.88
     Clos
    0.88
     passing
    0.86
     approach
    0.85
    peria
    0.84
    Activations Density 0.020%

    No Known Activations