© 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. 83885
    Prev
    Next
    INDEX
    Explanations

    specific names or items

    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
     SCIENT
    -0.76
    寫
    -0.76
     educativo
    -0.75
     gyro
    -0.75
     Civic
    -0.73
     Gie
    -0.72
     cister
    -0.71
    オト
    -0.71
    ptor
    -0.71
     homeowners
    -0.70
    POSITIVE LOGITS
     thermal
    1.13
     radiation
    1.02
     heat
    0.98
     temperature
    0.96
     heated
    0.86
     Hawking
    0.85
     quantum
    0.82
    heat
    0.81
    inities
    0.80
     Radiation
    0.80
    Activations Density 0.037%

    No Known Activations