© 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. 619
    Prev
    Next
    INDEX
    Explanations

    payment and entry

    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
    ksiyon
    -0.80
     yesterday
    -0.79
     breakfasts
    -0.75
     Nutzer
    -0.75
    MPa
    -0.73
     conferences
    -0.73
     edil
    -0.73
    ardt
    -0.72
    nyez
    -0.72
     televiz
    -0.71
    POSITIVE LOGITS
     admission
    1.16
     upstairs
    1.10
    admission
    1.09
    Admission
    1.05
     drink
    1.05
     ENTRY
    1.02
     glassware
    1.02
    strick
    1.01
     entry
    0.99
    ENTRY
    0.98
    Activations Density 0.025%

    No Known Activations