© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102240
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

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

    property names or keys in JSON objects and data structures, particularly in code contexts.

    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
    تفصیلات
    -1.93
    艄
    -1.93
     and
    -1.88
    都不能
    -1.72
    を発見
    -1.68
     of
    -1.59
     incredi
    -1.59
     situe
    -1.58
    のイメージ
    -1.58
    Тарих
    -1.57
    POSITIVE LOGITS
    _
    2.31
    Following
    2.08
    There
    2.03
    Being
    2.02
    :
    1.96
     sizable
    1.95
    -
    1.95
    Sometimes
    1.94
    Every
    1.93
    Despite
    1.92
    Activations Density 0.111%

    No Known Activations