© 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. 10-GEMMASCOPE-RES-131K
    4. 101911
    Prev
    Next
    INDEX
    Explanations

    code structs

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

    pointer declarations (the asterisk symbol `*` in C/C++ code that denotes pointer types).

    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
    {
    -2.00
    месте
    -1.88
    </h4>
    -1.62
    coledì
    -1.57
    {~
    -1.55
    стреча
    -1.55
     algun
    -1.53
    новь
    -1.52
    нутрен
    -1.49
     avec
    -1.48
    POSITIVE LOGITS
     that
    1.99
    咐
    1.59
    儼
    1.56
     it
    1.55
    
    1.48
     which
    1.46
    馀
    1.45
    皺
    1.44
     этого
    1.43
     mágica
    1.40
    Activations Density 0.004%

    No Known Activations