© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129570
    Prev
    Next
    INDEX
    Explanations

    prior art

    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
    irmanship
    -1.25
    %);
    -1.17
     витами
    -1.15
     रेटिंग
    -1.14
     españ
    -1.12
     doveva
    -1.09
     dovrebbe
    -1.06
    Tecnología
    -1.05
     tilgjenge
    -1.05
     pembelian
    -1.05
    POSITIVE LOGITS
    others
    1.34
     others
    1.34
    וּ
    1.23
     recent
    1.19
     recently
    1.18
     other
    1.12
    other
    1.03
    RECENT
    1.00
    recent
    0.99
     autres
    0.98
    Activations Density 0.156%

    No Known Activations