© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102567
    Prev
    Next
    INDEX
    Explanations

    pressure units (MPa)

    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
    亿美元
    -0.78
     inches
    -0.75
     BaseActivity
    -0.73
     Stahl
    -0.72
    PD
    -0.72
     寸
    -0.72
     it
    -0.71
     Extract
    -0.71
    Nobody
    -0.71
    GTG
    -0.69
    POSITIVE LOGITS
     MPa
    1.31
    MPa
    1.19
     MPA
    0.90
    MPA
    0.84
     barred
    0.84
    Ƣ
    0.81
    Watermark
    0.79
    Diving
    0.78
    兆
    0.77
     jacks
    0.75
    Activations Density 0.022%

    No Known Activations