© 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. 71647
    Prev
    Next
    INDEX
    Explanations

    programming and technical acronyms and suffixes

    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
    L
    -1.09
    Y
    -1.01
    為に
    -1.00
    S
    -0.98
    is
    -0.97
    R
    -0.94
    V
    -0.92
    K
    -0.90
     confirmed
    -0.90
     freakin
    -0.89
    POSITIVE LOGITS
    dians
    1.12
    xique
    1.09
    ilets
    1.02
    sä
    1.01
     couleurs
    1.01
    yı
    0.99
     bandas
    0.99
    CascadeType
    0.98
    sı
    0.98
    Waktu
    0.97
    Activations Density 0.063%

    No Known Activations