© 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. 98419
    Prev
    Next
    INDEX
    Explanations

    checking and verification

    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
     Anyone
    -1.14
     设置
    -1.02
     extinción
    -1.00
    cada
    -1.00
     Когда
    -0.99
     logró
    -0.99
    össe
    -0.98
     spielte
    -0.94
     mixes
    -0.94
    ⋒
    -0.94
    POSITIVE LOGITS
    mate
    1.33
    pointed
    1.31
    mating
    1.29
     Checker
    1.23
     difp
    1.21
     Checking
    1.20
     checker
    1.16
     pleaf
    1.16
    Check
    1.16
    kkkk
    1.13
    Activations Density 0.034%

    No Known Activations