© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84716
    Prev
    Next
    INDEX
    Explanations

    entire contents or the cover

    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
     its
    -1.48
     our
    -1.25
     their
    -1.24
    
    -0.84
     company
    -0.84
    ,:
    -0.84
     menschlichen
    -0.83
    copyTo
    -0.83
     other
    -0.82
     eléctrica
    -0.81
    POSITIVE LOGITS
     the
    0.98
     của
    0.93
     также
    0.89
    himovic
    0.84
    panou
    0.83
    Something
    0.82
    JIT
    0.81
    生態
    0.81
    chriften
    0.80
    вом
    0.79
    Activations Density 0.454%

    No Known Activations