© 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. 48150
    Prev
    Next
    INDEX
    Explanations

    Qi, G, q start words

    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
    ed
    -0.92
     năng
    -0.84
     소녀
    -0.77
    殊
    -0.77
     fotografia
    -0.76
     zusätzlichen
    -0.73
    ętr
    -0.72
     knew
    -0.72
    armament
    -0.71
    넨
    -0.71
    POSITIVE LOGITS
    真的
    0.84
    )<\
    0.84
    леку
    0.78
    альных
    0.77
     deviation
    0.77
     invalid
    0.76
    )$;
    0.76
    χε
    0.76
     выз
    0.75
    keted
    0.75
    Activations Density 0.003%

    No Known Activations