© 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. 57821
    Prev
    Next
    INDEX
    Explanations

    parts and components

    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
     enzymes
    -0.76
    memp
    -0.75
     producto
    -0.74
    范文
    -0.74
     product
    -0.74
     técnico
    -0.73
     blends
    -0.72
     produkter
    -0.71
     estadounidenses
    -0.70
     peruana
    -0.70
    POSITIVE LOGITS
     parts
    1.30
    parts
    1.29
     Parts
    1.27
    PARTS
    1.16
    Parts
    1.16
     PARTS
    1.14
     interchang
    1.10
     détach
    1.09
    零件
    1.02
     list
    0.98
    Activations Density 0.018%

    No Known Activations