© 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. 119979
    Prev
    Next
    INDEX
    Explanations

    const variable declarations

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

    the keyword "int" in programming code, especially when declaring integer variables or 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
     évé
    -1.83
     parfüm
    -1.80
    ⃙
    -1.69
    
    -1.68
    ètement
    -1.61
     rése
    -1.59
     parfü
    -1.58
     resistentes
    -1.56
    🧸
    -1.56
     tâ
    -1.55
    POSITIVE LOGITS
    5
    2.64
    8
    2.41
    3
    2.31
    7
    2.23
    9
    2.16
    4
    2.13
    6
    2.08
    2
    2.06
    1
    2.03
     also
    1.75
    Activations Density 0.007%

    No Known Activations