© 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. 22-GEMMASCOPE-RES-131K
    7. 98306
    Prev
    Next
    INDEX
    Explanations

    South African countries

    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_22/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
    "
    -1.55
     not
    -1.48
     like
    -1.30
    EDING
    -1.30
     "
    -1.26
     them
    -1.24
    月中
    -1.24
    主播
    -1.23
    swar
    -1.23
    方がいい
    -1.22
    POSITIVE LOGITS
     Johannesburg
    1.88
    fontein
    1.36
     Pretoria
    1.36
    ContentLoaded
    1.32
    atouille
    1.26
    =");
    1.23
     rind
    1.23
    快要
    1.18
    dorp
    1.18
     bela
    1.16
    Activations Density 0.032%

    No Known Activations