© 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. 9155
    Prev
    Next
    INDEX
    Explanations

    path to a goal or journey

    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
    鹮
    -2.17
    骤
    -2.11
    抬手
    -2.09
    </h3>
    -2.06
     baz
    -2.05
    眨眼
    -2.03
    得不
    -1.93
    ,
    -1.89
    嵜
    -1.86
     parachoque
    -1.82
    POSITIVE LOGITS
    </b>
    2.44
    s
    2.27
    t
    2.27
     They
    2.03
     Its
    2.00
    是
    1.98
     path
    1.91
    n
    1.90
     obtain
    1.88
     paths
    1.84
    Activations Density 0.028%

    No Known Activations