© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103378
    Prev
    Next
    INDEX
    Explanations

    earthmoving and excavation

    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
     여자
    -0.83
    IBLES
    -0.78
    水面
    -0.77
    ꯅ
    -0.77
    ůl
    -0.76
     woda
    -0.76
     Вода
    -0.75
    Holger
    -0.74
     sabotage
    -0.73
    stahl
    -0.73
    POSITIVE LOGITS
     earth
    1.34
     fill
    1.29
     excavated
    1.27
     material
    1.26
     removed
    1.17
     dumped
    1.10
    earth
    1.09
     hauled
    1.05
     spoil
    1.05
    fill
    1.03
    Activations Density 0.022%

    No Known Activations