© 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. 22-GEMMASCOPE-RES-131K
    4. 11111
    Prev
    Next
    INDEX
    Explanations

    code constructs like `do`, `if`, `for`

    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_22/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
    eloma
    -1.09
     mengirim
    -1.00
    Boat
    -0.98
    jezd
    -0.95
    othes
    -0.92
    выя
    -0.91
    Kalau
    -0.91
    Lokasi
    -0.90
     mengirimkan
    -0.89
     белого
    -0.89
    POSITIVE LOGITS
     baden
    0.97
    СТВ
    0.92
    uropa
    0.88
    ACITY
    0.88
    颪
    0.85
    istaa
    0.85
     maailman
    0.85
     القلب
    0.85
    idings
    0.83
    மான
    0.83
    Activations Density 0.007%

    No Known Activations