© 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. 34-GEMMASCOPE-RES-131K
    7. 4252
    Prev
    Next
    INDEX
    Explanations

    code intents and structures

    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
    給
    -1.04
    Giving
    -0.79
     giving
    -0.79
     Giving
    -0.79
    zei
    -0.78
    给
    -0.76
     valleys
    -0.75
     給
    -0.75
    DAS
    -0.72
     Smithsonian
    -0.72
    POSITIVE LOGITS
    动物
    0.75
    竟然
    0.75
    かったです
    0.72
     Chats
    0.69
     turma
    0.68
    キット
    0.67
    παι
    0.66
    Charging
    0.65
    ਾਰ
    0.65
     fulfil
    0.65
    Activations Density 0.069%

    No Known Activations