© 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. 36570
    Prev
    Next
    INDEX
    Explanations

    of the [noun]

    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
     Puedes
    -1.42
     множество
    -1.30
     grève
    -1.27
    講師
    -1.24
     Alguns
    -1.23
     Aún
    -1.23
    Läs
    -1.22
     -¿
    -1.21
     jenen
    -1.20
     związ
    -1.15
    POSITIVE LOGITS
     these
    1.83
     this
    1.81
     our
    1.70
     each
    1.65
     such
    1.35
     already
    1.30
     both
    1.28
     ilyen
    1.28
     only
    1.24
     previous
    1.23
    Activations Density 0.275%

    No Known Activations