© 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. 12393
    Prev
    Next
    INDEX
    Explanations

    such as, committed to, will come

    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
     प्रोड
    -1.43
    numOf
    -1.34
     नंबर
    -1.26
    婓
    -1.20
     данной
    -1.19
    IfExists
    -1.17
     huiles
    -1.16
    醣
    -1.14
     फिल्म
    -1.12
    papier
    -1.11
    POSITIVE LOGITS
     our
    1.72
     важ
    1.34
    往往
    1.29
    ־ה
    1.27
    一方で
    1.27
    こうした
    1.24
     enjoy
    1.22
     buscando
    1.21
     intensa
    1.18
    仍然
    1.17
    Activations Density 0.013%

    No Known Activations