© 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. 25688
    Prev
    Next
    INDEX
    Explanations

    first person statements

    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
     demais
    -0.98
     بسر
    -0.94
    setItems
    -0.90
    Folks
    -0.89
    越南
    -0.88
    太多
    -0.87
    too
    -0.84
    ૪
    -0.84
    FWIW
    -0.83
     my
    -0.82
    POSITIVE LOGITS
     usually
    1.14
     don
    1.03
     fumée
    0.99
     also
    0.97
     kinda
    0.95
    ariously
    0.95
     iria
    0.94
     mainly
    0.92
     basically
    0.89
     acidente
    0.89
    Activations Density 0.102%

    No Known Activations