© 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. 34-GEMMASCOPE-RES-131K
    7. 38421
    Prev
    Next
    INDEX
    Explanations

    Oracle SQL

    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
    胪
    -0.90
     Kond
    -0.87
    ẫu
    -0.84
     ATR
    -0.78
     NEG
    -0.76
     Gim
    -0.76
    손
    -0.74
     CCTV
    -0.73
    Cita
    -0.73
     COC
    -0.73
    POSITIVE LOGITS
    Oracle
    1.63
     Oracle
    1.58
    oracle
    1.41
     oracle
    1.27
     ORA
    1.09
    ORA
    1.08
     SCOTT
    1.06
    Oregon
    0.95
    SCOTT
    0.94
    Flashback
    0.90
    Activations Density 0.120%

    No Known Activations