© 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. 10-GEMMASCOPE-RES-131K
    7. 19757
    Prev
    Next
    INDEX
    Explanations

    file i/o and type declarations

    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_10/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
     was
    -1.60
    馓
    -1.35
     misi
    -1.31
    \.
    -1.26
     Saltar
    -1.24
     bolsos
    -1.23
     aikaa
    -1.23
     blusa
    -1.23
    -#
    -1.22
    .《
    -1.22
    POSITIVE LOGITS
    0
    1.69
     Może
    1.47
    .
    1.38
    Your
    1.27
    muta
    1.26
    だけです
    1.26
    Our
    1.25
     їх
    1.23
     quieren
    1.21
    __":
    1.20
    Activations Density 0.012%

    No Known Activations