© 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. 104190
    Prev
    Next
    INDEX
    Explanations

    analyst, cost, Bill, child, registry, data, run

    np_acts-logits-general · gemini-2.5-flash-lite

    repeated or duplicated words appearing consecutively or in close proximity.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    ↵
    -1.63
     späteren
    -1.61
    %",
    -1.56
     posteriormente
    -1.54
     inicialmente
    -1.45
     alguien
    -1.41
     stroj
    -1.38
     primero
    -1.35
     somebody
    -1.34
    sukienka
    -1.34
    POSITIVE LOGITS
    2
    2.03
    7
    1.61
    the
    1.58
     terutama
    1.52
    to
    1.47
    6
    1.47
    sistent
    1.45
    w
    1.44
     torino
    1.43
    which
    1.41
    Activations Density 0.118%

    No Known Activations