© 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. 65237
    Prev
    Next
    INDEX
    Explanations

    examples of usage

    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
     of
    -2.53
    ↵↵
    -1.66
    境的
    -1.64
     politiet
    -1.61
    珦
    -1.55
     wszel
    -1.55
     Що
    -1.52
     seluruh
    -1.52
     time
    -1.51
     nawet
    -1.48
    POSITIVE LOGITS
    salms
    1.77
    “
    1.52
    ном
    1.51
    ван
    1.48
    这样
    1.47
     ”
    1.45
    のお店
    1.45
    mbrie
    1.45
    notated
    1.44
    notations
    1.38
    Activations Density 0.039%

    No Known Activations