© 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. 82542
    Prev
    Next
    INDEX
    Explanations

    scientific notation

    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
     kväll
    -0.82
     förra
    -0.79
     cursive
    -0.78
     öppna
    -0.77
     przecież
    -0.77
    Measurement
    -0.76
    禎
    -0.76
    łeś
    -0.75
     Measurements
    -0.74
     SSN
    -0.73
    POSITIVE LOGITS
    €“
    0.94
     Libertadores
    0.88
     tham
    0.86
     VEGAS
    0.85
     côn
    0.84
    бирать
    0.82
     daughter
    0.82
    サート
    0.81
    heet
    0.80
    Stable
    0.80
    Activations Density 0.009%

    No Known Activations