© 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. 2547
    Prev
    Next
    INDEX
    Explanations

    solar, photovoltaic, PV

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ัฒ
    -0.95
     ويكيپيديا
    -0.89
    coca
    -0.87
     reopening
    -0.83
    sividad
    -0.82
    odore
    -0.79
    
    -0.79
    nsic
    -0.79
     reopened
    -0.77
     speedometer
    -0.77
    POSITIVE LOGITS
     solar
    3.70
     Solar
    3.19
    Solar
    2.94
    solar
    2.92
     photovoltaic
    2.44
     SOLAR
    2.14
     PV
    2.08
     güneş
    2.06
     солне
    2.03
     sun
    2.02
    Activations Density 0.043%

    No Known Activations