© 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. 93030
    Prev
    Next
    INDEX
    Explanations

    run with direction or context

    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
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -1.16
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.15
    ↵↵↵↵↵↵↵↵↵↵
    -1.14
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.11
    ↵↵↵↵↵↵↵↵
    -1.11
    ↵↵↵↵↵↵↵↵↵↵↵
    -1.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.06
    ↵↵↵↵↵↵
    -1.05
    ↵↵↵↵↵↵↵
    -1.05
     that
    -1.05
    POSITIVE LOGITS
     errands
    1.52
     into
    1.30
     gamut
    1.27
    Apesar
    1.15
    ка
    1.15
    Ainda
    1.14
     ran
    1.09
    ämme
    1.09
     kiếm
    1.05
    Mesmo
    1.05
    Activations Density 0.029%

    No Known Activations