© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65412
    Prev
    Next
    INDEX
    Explanations

    time delta and numerical parameters

    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
    詡
    -0.85
    liehen
    -0.81
    初期
    -0.79
     Hyman
    -0.76
    chul
    -0.73
    この日は
    -0.72
    Déc
    -0.71
     compatri
    -0.70
     Polka
    -0.70
     initially
    -0.70
    POSITIVE LOGITS
     dt
    2.06
     delta
    1.77
    dt
    1.70
     Delta
    1.60
     DT
    1.59
    delta
    1.52
     elapsed
    1.45
    deltaTime
    1.39
     Δ
    1.38
     deltaTime
    1.36
    Activations Density 0.006%

    No Known Activations