© 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. 12217
    Prev
    Next
    INDEX
    Explanations

    reaching a state or point

    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
    9
    -2.05
    again
    -1.94
    am
    -1.90
    very
    -1.78
     ^
    -1.74
    ”
    -1.71
    4
    -1.71
    3
    -1.64
    \
    -1.63
    "
    -1.62
    POSITIVE LOGITS
     навіть
    1.82
    Gnome
    1.77
     sogar
    1.77
     nawet
    1.76
    各種
    1.70
     можли
    1.66
    ‫‪
    1.65
     even
    1.59
     zelfs
    1.56
    cardigan
    1.55
    Activations Density 0.008%

    No Known Activations