© 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. 34-GEMMASCOPE-RES-131K
    7. 98790
    Prev
    Next
    INDEX
    Explanations

    division into groups or cases

    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
     作り方
    -1.31
     называется
    -1.17
     berbagai
    -1.14
     pensó
    -1.13
    Foi
    -1.11
    なかな
    -1.11
    Quanto
    -1.09
    Efe
    -1.06
     conoció
    -1.06
     THEIR
    -1.04
    POSITIVE LOGITS
     case
    2.38
     cases
    1.91
     scenario
    1.91
     group
    1.74
     situation
    1.70
     dataset
    1.59
     samples
    1.58
     category
    1.57
     option
    1.45
    case
    1.42
    Activations Density 0.148%

    No Known Activations