© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57413
    Prev
    Next
    INDEX
    Explanations

    observation or observed

    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
     bekijken
    -0.90
    vagrant
    -0.78
    encontra
    -0.70
    mercado
    -0.69
     nicely
    -0.68
    琬
    -0.66
     verschw
    -0.65
     hộ
    -0.64
    っ
    -0.64
     feels
    -0.64
    POSITIVE LOGITS
     observation
    1.50
     observations
    1.42
     Observation
    1.35
     Observe
    1.27
     observable
    1.25
    observation
    1.24
    Observation
    1.23
     observance
    1.23
     OBSERV
    1.21
     observed
    1.20
    Activations Density 0.034%

    No Known Activations