© 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. 22-GEMMASCOPE-RES-131K
    4. 71290
    Prev
    Next
    INDEX
    Explanations

    choice between alternatives

    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
     etc
    -1.11
    hésite
    -0.94
    مرار
    -0.92
    、
    -0.88
     Certaines
    -0.87
     I
    -0.87
     could
    -0.86
     agrega
    -0.85
     Kriterien
    -0.85
     Prenez
    -0.84
    POSITIVE LOGITS
     versus
    1.15
     vs
    1.13
     while
    1.12
     whereas
    1.06
     mientras
    1.02
    vriende
    0.95
     then
    0.95
    另一种
    0.93
    While
    0.93
    quanto
    0.92
    Activations Density 0.119%

    No Known Activations