© 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. 12023
    Prev
    Next
    INDEX
    Explanations

    convert from source to destination

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

    method names that involve conversion or transformation operations, particularly "ToString" and "To" followed by a type or format name.

    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
    但也
    -1.86
     to
    -1.81
    us
    -1.80
    ul
    -1.61
    鬭
    -1.55
    ll
    -1.55
    C
    -1.53
    
    -1.52
    z
    -1.48
    "—
    -1.47
    POSITIVE LOGITS
     från
    1.77
     sorta
    1.74
     từ
    1.68
     после
    1.64
    ↵↵
    1.60
     şeker
    1.52
    จาก
    1.52
     dari
    1.49
     saludables
    1.49
    焄
    1.48
    Activations Density 0.002%

    No Known Activations