© 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. 35820
    Prev
    Next
    INDEX
    Explanations

    absence or lack

    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
     also
    -0.88
     TAMBÉM
    -0.86
     sirup
    -0.85
    ENCIÓN
    -0.84
     mek
    -0.82
     miliar
    -0.78
    octanol
    -0.78
    iros
    -0.77
     samar
    -0.77
     often
    -0.75
    POSITIVE LOGITS
     they
    1.20
     empty
    1.12
     there
    1.08
     côtes
    1.06
     débuts
    1.06
    varnothing
    1.05
    isEmpty
    1.02
     isempty
    1.02
     emptiness
    1.02
    日を
    1.02
    Activations Density 0.004%

    No Known Activations