© 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. 966
    Prev
    Next
    INDEX
    Explanations

    occupying specific market niches

    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
    емости
    -0.93
    bės
    -0.85
    ettu
    -0.77
    ppia
    -0.75
    
    -0.75
    UNGE
    -0.73
    
    -0.72
     listado
    -0.72
    իլ
    -0.71
    ὄ
    -0.71
    POSITIVE LOGITS
     niche
    4.75
     niches
    3.77
    niche
    3.38
     Niche
    3.22
     carve
    2.25
     carved
    2.20
     nich
    2.06
     carving
    2.03
     nic
    1.61
     NIC
    1.59
    Activations Density 0.034%

    No Known Activations