© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 117586
    Prev
    Next
    INDEX
    Explanations

    solar cells

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

    The neuron fires strongly on terms naming or describing solar-power facilities and related renewable-energy infrastructure (e.g. “Solar,” “Power,” “Station,” “plant,” “electricity”), effectively spotting passages about solar energy sites and equipment.

    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
     Storage
    -0.82
     storage
    -0.80
    店的
    -0.70
    DataOutputStream
    -0.69
    Ferdinand
    -0.69
     Egli
    -0.68
    storage
    -0.67
    página
    -0.66
    Storage
    -0.66
    rill
    -0.65
    POSITIVE LOGITS
     solar
    3.38
     photovoltaic
    2.92
    solar
    2.50
     PV
    2.47
    Solar
    2.45
     Solar
    2.42
    PV
    2.22
     SOLAR
    1.98
     pv
    1.98
    pv
    1.81
    Activations Density 0.030%

    No Known Activations