© 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. 22-GEMMASCOPE-RES-131K
    7. 74912
    Prev
    Next
    INDEX
    Explanations

    probability and equations

    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_22/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
     już
    -1.34
     уже
    -1.24
     Although
    -1.09
     of
    -1.05
    точно
    -1.02
     служба
    -1.01
    чего
    -0.99
     AtomicInteger
    -0.99
     lehet
    -0.99
     círculo
    -0.97
    POSITIVE LOGITS
     others
    1.15
     clés
    0.94
     étudiant
    0.92
     récompenses
    0.91
    يتي
    0.91
    rália
    0.90
    빡
    0.90
    зец
    0.88
     everyone
    0.88
     Traces
    0.88
    Activations Density 0.023%

    No Known Activations