© 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. 102597
    Prev
    Next
    INDEX
    Explanations

    car horsepower and specifications

    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
    倭
    -0.92
     本店
    -0.87
     analisis
    -0.84
     campana
    -0.82
     both
    -0.82
     Constan
    -0.82
     買取
    -0.81
     कोशिश
    -0.80
     whose
    -0.79
     busto
    -0.79
    POSITIVE LOGITS
     evtl
    0.88
    ))+
    0.87
    sbereich
    0.77
     chè
    0.75
    \",\
    0.75
    laria
    0.73
    potentially
    0.73
     linken
    0.72
    Ë
    0.71
     efectu
    0.70
    Activations Density 0.001%

    No Known Activations