© 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. 117803
    Prev
    Next
    INDEX
    Explanations

    wetland, marsh, swamp, flooded areas

    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
    富士山
    -0.76
    nueva
    -0.75
    Medidas
    -0.73
     personaggio
    -0.72
     turbidity
    -0.71
    閉店
    -0.70
    Abel
    -0.70
    Edad
    -0.70
    Irrigation
    -0.70
     agave
    -0.69
    POSITIVE LOGITS
     wetland
    1.30
     wetlands
    0.97
     Wetland
    0.91
     marsh
    0.86
     facult
    0.85
     saturated
    0.85
    вам
    0.84
    Pub
    0.83
     depression
    0.82
     Signatures
    0.82
    Activations Density 0.008%

    No Known Activations