© 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. 34-GEMMASCOPE-RES-131K
    4. 86953
    Prev
    Next
    INDEX
    Explanations

    Japanese honorofics, errors, and code imports

    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_34/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
    を
    -0.97
    声が
    -0.94
    Climat
    -0.93
     slik
    -0.90
     coffret
    -0.84
    !』
    -0.84
     compositor
    -0.83
    ?』
    -0.83
     some
    -0.81
     bedste
    -0.81
    POSITIVE LOGITS
     mismas
    1.00
    rativa
    0.98
    Previously
    0.97
     cinza
    0.96
     voordeel
    0.95
     nguyen
    0.95
    newblock
    0.94
     Previously
    0.94
    atisfactory
    0.93
     oír
    0.92
    Activations Density 0.002%

    No Known Activations