© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116256
    Prev
    Next
    INDEX
    Explanations

    construction materials

    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
    balleur
    -0.82
    URIDAD
    -0.76
     ucap
    -0.74
    reifen
    -0.74
    Fet
    -0.72
     PTC
    -0.72
     cancerous
    -0.71
     LLVM
    -0.70
     Halen
    -0.70
     recycla
    -0.69
    POSITIVE LOGITS
     plaster
    3.13
     mortar
    2.75
     штука
    2.36
     stucco
    2.28
     plastered
    2.25
     brick
    2.23
     masonry
    2.17
     Plaster
    2.03
    mortar
    2.02
     cement
    1.92
    Activations Density 0.039%

    No Known Activations