© 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. 98679
    Prev
    Next
    INDEX
    Explanations

    assess, process, and improve

    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
    があり
    -1.41
     poiché
    -1.41
    ですが
    -1.37
    Õ
    -1.34
    そのため
    -1.29
    ׳
    -1.29
    ʻ
    -1.27
    がある
    -1.27
     inay
    -1.25
    なので
    -1.23
    POSITIVE LOGITS
     and
    2.80
     or
    2.13
     казалось
    1.42
    },
    1.35
     bzw
    1.32
     albeit
    1.29
     not
    1.26
     With
    1.21
     During
    1.20
    はな
    1.18
    Activations Density 0.050%

    No Known Activations