© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112692
    Prev
    Next
    INDEX
    Explanations

    data table components

    np_acts-logits-general · gemini-2.5-flash-lite

    references to HTML or data tables in technical programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     –
    -1.24
     and
    -1.23
    achten
    -1.18
     talvez
    -1.11
    achio
    -1.07
    flexGrow
    -1.05
     prefeitura
    -1.05
     تعدى
    -1.05
     but
    -1.04
     however
    -1.04
    POSITIVE LOGITS
     any
    1.22
    近年来
    1.16
    ון
    1.16
    قد
    1.15
    šanu
    1.14
    ช่วง
    1.13
    šanai
    1.13
     tillgäng
    1.13
    一些
    1.11
     Selv
    1.11
    Activations Density 0.062%

    No Known Activations