© 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. 22-GEMMASCOPE-RES-131K
    7. 36377
    Prev
    Next
    INDEX
    Explanations

    programming and mathematical definitions

    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
    <bos>
    -1.08
     ajuta
    -1.04
    なので
    -1.00
    这也
    -0.99
     vedea
    -0.98
     次元
    -0.97
    是怎么回事
    -0.96
    を
    -0.96
     firs
    -0.93
     vektör
    -0.92
    POSITIVE LOGITS
     nena
    1.27
    ┬
    1.13
     jotka
    1.13
     sitten
    1.12
     chère
    1.12
     latas
    1.11
     engran
    1.10
    ፝
    1.09
     CountDown
    1.07
    ݯ
    1.07
    Activations Density 0.007%

    No Known Activations