© 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. 118501
    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
    河南
    -1.00
    晟
    -0.94
    ७
    -0.94
    ulée
    -0.92
    После
    -0.90
    STRICT
    -0.90
     Maschine
    -0.89
    anyone
    -0.88
    ఢ
    -0.87
    江西
    -0.86
    POSITIVE LOGITS
    <bos>
    1.25
    ebly
    1.20
     Erfüllung
    1.09
     Bearbeitung
    1.08
    んじゃ
    1.05
     belangrijkste
    1.05
    ttää
    1.05
    0
    1.05
    澁
    1.02
    这让
    1.01
    Activations Density 0.051%

    No Known Activations