© 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. 35670
    Prev
    Next
    INDEX
    Explanations

    code comments and documentation

    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
    が
    -1.06
    lib
    -1.00
    он
    -0.99
    This
    -0.96
     ImageButton
    -0.93
    just
    -0.93
    will
    -0.93
     will
    -0.93
     América
    -0.93
    氛
    -0.92
    POSITIVE LOGITS
    側は
    1.02
    setNome
    1.00
     aparcamiento
    0.98
     and
    0.98
     tasks
    0.95
     Kontrolle
    0.95
    接著
    0.94
    ❖
    0.93
     daje
    0.93
    Geld
    0.91
    Activations Density 0.019%

    No Known Activations