© 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. 80715
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
    lieren
    -0.95
    rhos
    -0.91
    mismo
    -0.86
    dedores
    -0.85
    messageInfo
    -0.84
     potret
    -0.84
    prendre
    -0.84
     woorden
    -0.84
     Although
    -0.82
    털
    -0.82
    POSITIVE LOGITS
    5
    1.19
    8
    1.00
    6
    0.98
    7
    0.97
    2
    0.95
    3
    0.95
    9
    0.94
    1
    0.88
    Zim
    0.86
    achieve
    0.85
    Activations Density 0.144%

    No Known Activations