© 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. 91167
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and positions

    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
     Though
    -1.20
     Those
    -1.09
     There
    -1.07
     That
    -1.07
    Though
    -1.05
     what
    -1.04
     that
    -0.98
     Despite
    -0.97
     However
    -0.96
    LEGGI
    -0.93
    POSITIVE LOGITS
     новом
    1.03
    Legende
    0.99
    甚至
    0.93
    time
    0.92
    这样
    0.90
    渐渐
    0.86
     gegebenen
    0.85
    汚
    0.85
    apparently
    0.85
    handles
    0.84
    Activations Density 0.003%

    No Known Activations