© 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. 11766
    Prev
    Next
    INDEX
    Explanations

    technical terms

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

    technical terms referring to component sequences or structures within systems.

    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
     parede
    -1.54
     комплекте
    -1.42
     élas
    -1.41
    椟
    -1.41
     Terkait
    -1.40
     avesse
    -1.37
     religione
    -1.35
    THEN
    -1.34
    gmail
    -1.34
     ecran
    -1.34
    POSITIVE LOGITS
     that
    2.89
     for
    2.67
     of
    2.34
     by
    2.20
     which
    2.05
     where
    1.95
     to
    1.79
     on
    1.77
     or
    1.65
    ,
    1.48
    Activations Density 0.194%

    No Known Activations