© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71152
    Prev
    Next
    INDEX
    Explanations

    whether you

    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
     素描
    -1.64
     uniquement
    -1.46
    PasswordEncoder
    -1.46
    offers
    -1.45
     choisis
    -1.42
     loto
    -1.41
     diza
    -1.38
     если
    -1.37
     jei
    -1.36
     quando
    -1.34
    POSITIVE LOGITS
     there
    2.30
     it
    2.05
     this
    2.02
     you
    1.90
     we
    1.66
    我又
    1.56
     or
    1.52
     queda
    1.50
     assorted
    1.38
     zgodnie
    1.33
    Activations Density 0.022%

    No Known Activations