© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33807
    Prev
    Next
    INDEX
    Explanations

    consulting and engineering firms

    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
    postcode
    -0.88
    ParseTree
    -0.82
    ędzy
    -0.82
     ایالات
    -0.77
    asign
    -0.77
    oxide
    -0.76
     Residence
    -0.75
    utsal
    -0.75
     Culinary
    -0.75
    depend
    -0.74
    POSITIVE LOGITS
     consulting
    1.63
     consultants
    1.60
     engineering
    1.45
     Consulting
    1.34
     consultant
    1.30
     consultancy
    1.28
     Consultants
    1.24
    Consulting
    1.21
     engineers
    1.15
    consult
    1.06
    Activations Density 0.027%

    No Known Activations