© 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. 76179
    Prev
    Next
    INDEX
    Explanations

    for conditions and 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
    ▿
    -0.91
    ductory
    -0.88
    quilo
    -0.87
    idiary
    -0.86
    ")(
    -0.86
    🧖
    -0.85
    žev
    -0.85
     העולם
    -0.85
    ressee
    -0.85
    asă
    -0.85
    POSITIVE LOGITS
     values
    1.76
     cases
    1.45
     sufficiently
    1.41
     moderate
    1.40
     reasons
    1.38
     small
    1.35
     temperatures
    1.34
     purposes
    1.34
     large
    1.34
     given
    1.34
    Activations Density 0.054%

    No Known Activations