© 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. 79
    Prev
    Next
    INDEX
    Explanations

    "lib" followed by software components

    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
    timmt
    -1.97
     those
    -1.91
     Makes
    -1.84
    琹
    -1.80
     lebte
    -1.79
    釙
    -1.76
     gehörte
    -1.73
    Ꮮ
    -1.72
    ꪔ
    -1.68
    ʬ
    -1.66
    POSITIVE LOGITS
     of
    2.91
    2
    2.42
    3
    2.14
    8
    2.00
    \
    1.98
    6
    1.79
    /
    1.65
     assures
    1.64
    又在
    1.63
    5
    1.63
    Activations Density 0.026%

    No Known Activations