© 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. 48561
    Prev
    Next
    INDEX
    Explanations

    planet and earth

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

    The neuron chiefly responds to words referring to the Earth or its environment (e.g. “Earth,” “planet,” “environmental”).

    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
    IED
    -0.84
    ydı
    -0.75
    aconda
    -0.75
    oslav
    -0.74
    acán
    -0.72
    itä
    -0.72
    役に
    -0.71
     Publikum
    -0.71
    nologia
    -0.70
     Nassau
    -0.70
    POSITIVE LOGITS
     planet
    4.47
     Earth
    3.61
     earth
    3.41
     Planet
    3.22
    planet
    3.17
    Planet
    3.03
    地球
    3.00
    Earth
    2.97
     globe
    2.81
    earth
    2.61
    Activations Density 0.049%

    No Known Activations