© 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. 91896
    Prev
    Next
    INDEX
    Explanations

    assembly

    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
     USS
    -0.81
     aad
    -0.77
     towing
    -0.76
     nft
    -0.73
     созна
    -0.71
     campeonato
    -0.71
     steam
    -0.71
    atorul
    -0.71
    汽
    -0.70
     MAF
    -0.69
    POSITIVE LOGITS
     assembly
    2.08
    assembly
    1.95
    assemb
    1.76
     assemb
    1.75
     assemblies
    1.72
     Assembly
    1.67
    Assembly
    1.67
     assemble
    1.66
     assembler
    1.63
     assembling
    1.55
    Activations Density 0.039%

    No Known Activations