© 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. 34-GEMMASCOPE-RES-131K
    7. 110825
    Prev
    Next
    INDEX
    Explanations

    processing and materials

    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_34/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
    ఽ
    -1.13
    ☫
    -1.09
     dreadful
    -1.04
    stest
    -1.03
    🫃
    -1.00
    呖
    -0.99
    なければ
    -0.98
     ILogger
    -0.97
     inesper
    -0.96
    ౬
    -0.96
    POSITIVE LOGITS
     from
    1.20
     and
    1.16
     during
    1.14
    just
    1.11
     with
    1.09
     wezen
    1.05
     khusus
    1.01
     Daarna
    1.00
     entirely
    0.99
     сахара
    0.99
    Activations Density 0.068%

    No Known Activations