© 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. 82567
    Prev
    Next
    INDEX
    Explanations

    mutation variants

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

    numerical sequences, particularly when they appear in scientific notation, coordinates, or genetic sequences.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     양
    -0.77
     Fost
    -0.74
    CommandHandler
    -0.72
     graces
    -0.71
     groves
    -0.69
    ليف
    -0.68
     增加
    -0.67
    CRP
    -0.67
    rha
    -0.66
    cM
    -0.65
    POSITIVE LOGITS
     multip
    0.79
     JSTOR
    0.72
     penetration
    0.72
     Allied
    0.71
     Associated
    0.71
     За
    0.69
    Banana
    0.69
     allied
    0.69
    ringa
    0.68
     Games
    0.68
    Activations Density 0.163%

    No Known Activations