© 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. 34-GEMMASCOPE-RES-131K
    4. 47878
    Prev
    Next
    INDEX
    Explanations

    html tags and copyright notices

    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_34/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
     with
    -1.52
     by
    -1.34
     without
    -1.19
     in
    -1.10
     fairly
    -1.08
     as
    -1.06
     not
    -1.06
     very
    -1.06
     which
    -1.05
     on
    -1.03
    POSITIVE LOGITS
     fie
    1.09
     COSTS
    1.09
     새로운
    0.99
    还不
    0.98
     streamlining
    0.97
    ihnachten
    0.96
     モダン
    0.96
     procedimentos
    0.96
    for
    0.96
     dismal
    0.96
    Activations Density 0.001%

    No Known Activations