© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91585
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
     geben
    -0.77
    usura
    -0.76
    િ
    -0.75
    OBJECTIVES
    -0.74
    graves
    -0.73
    paque
    -0.72
    unjukkan
    -0.71
     remise
    -0.71
     Dich
    -0.69
    陋
    -0.69
    POSITIVE LOGITS
    — 
    0.93
    Args
    0.88
    titudine
    0.82
    tedrale
    0.81
    konzept
    0.79
     Bakterien
    0.79
     SAFETY
    0.77
     Boucher
    0.77
    safety
    0.75
    verbrauch
    0.75
    Activations Density 0.002%

    No Known Activations