© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62689
    Prev
    Next
    INDEX
    Explanations

    measurement attributes and quantities

    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
     verstär
    -0.85
    cible
    -0.84
     aproximadamente
    -0.83
     estratégico
    -0.82
     preuve
    -0.82
     vidrio
    -0.81
    ountain
    -0.81
     negociaciones
    -0.80
    łość
    -0.80
     riesgo
    -0.80
    POSITIVE LOGITS
     temperature
    1.65
     volume
    1.43
     humidity
    1.38
     height
    1.33
     length
    1.27
     total
    1.25
     altitude
    1.19
     voltage
    1.15
     duration
    1.13
     calories
    1.13
    Activations Density 0.234%

    No Known Activations