© 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. 10-GEMMASCOPE-RES-131K
    7. 257
    Prev
    Next
    INDEX
    Explanations

    software components and libraries

    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
    兩
    -1.58
     two
    -1.36
    Three
    -1.27
     three
    -1.22
    Two
    -1.21
     caminar
    -1.21
     corregir
    -1.20
     hacerle
    -1.20
    两
    -1.19
     fabricar
    -1.18
    POSITIVE LOGITS
    </b>
    1.23
     suci
    1.20
     in
    1.20
     Dinamarca
    1.16
     tanong
    1.16
     definiti
    1.15
     pastillas
    1.15
     frond
    1.13
     (…)
    1.13
     $<$
    1.12
    Activations Density 0.326%

    No Known Activations