© 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. 42553
    Prev
    Next
    INDEX
    Explanations

    Jedi, Avengers, locksmith, Shawn, LGBTQ

    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
    \
    -2.88
    м
    -2.70
     {
    -2.70
    <bos>
    -2.50
     --
    -2.47
     —
    -2.45
    er
    -2.42
        
    -2.42
    _{
    -2.41
    􀂃
    -2.39
    POSITIVE LOGITS
    镦
    2.61
    咴
    2.44
     pastikan
    2.36
     cuaca
    2.30
    囖
    2.27
    when
    2.22
     lancia
    2.20
    幃
    2.20
     櫃
    2.19
     』
    2.19
    Activations Density 0.001%

    No Known Activations