© 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. 120011
    Prev
    Next
    INDEX
    Explanations

    byzantine fault tolerant protocol

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

    word fragments that are part of proper nouns or brand names, particularly those ending in common suffixes like "-ant", "-us", "-i", or "-es".

    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
    4
    -1.77
    1
    -1.74
     -
    -1.71
     will
    -1.63
    d
    -1.59
    It
    -1.56
    k
    -1.53
    6
    -1.45
    3
    -1.45
    5
    -1.45
    POSITIVE LOGITS
    motorola
    1.52
    Orléans
    1.52
    weightedMode
    1.48
     misschien
    1.47
     \!
    1.42
    řit
    1.41
     帽子
    1.39
     入っ
    1.39
    trauer
    1.38
    сшта
    1.38
    Activations Density 0.263%

    No Known Activations