© 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. 76787
    Prev
    Next
    INDEX
    Explanations

    data acquisition instruments

    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
     Kompon
    -0.90
     QoS
    -0.88
     citado
    -0.87
     permainan
    -0.86
    kops
    -0.83
     empate
    -0.81
    弩
    -0.81
    spender
    -0.79
     Ива
    -0.78
     bagi
    -0.78
    POSITIVE LOGITS
     instrument
    1.13
     acquisitions
    1.09
    instrument
    1.07
     Lab
    1.06
     Instrument
    1.05
     adquisición
    1.04
     instruments
    1.04
     acquisition
    1.02
     voltage
    1.01
     acquis
    0.99
    Activations Density 0.014%

    No Known Activations