© 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. 10-GEMMASCOPE-RES-131K
    7. 118869
    Prev
    Next
    INDEX
    Explanations

    volunteer roles and organizations

    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_10/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
     quando
    -2.83
    uſe
    -2.72
     lorsque
    -2.72
     lorsqu
    -2.42
    倌
    -2.38
    毳
    -2.36
    
    -2.34
     wanneer
    -2.30
    いえば
    -2.28
    翃
    -2.28
    POSITIVE LOGITS
    </strong>
    3.56
    </h3>
    3.05
    Also
    2.86
    While
    2.80
    Even
    2.72
    Although
    2.70
    Since
    2.69
    The
    2.56
    Currently
    2.55
    After
    2.44
    Activations Density 0.002%

    No Known Activations