© 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. 12817
    Prev
    Next
    INDEX
    Explanations

    code snippets, programming keywords

    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
    atisch
    -1.02
    देश
    -1.02
    всем
    -1.01
     condomínio
    -0.99
    ṝ
    -0.98
     bulan
    -0.97
    Укра
    -0.97
     sekarang
    -0.96
     Komun
    -0.95
    vaný
    -0.94
    POSITIVE LOGITS
     and
    1.03
    ociação
    0.99
    filepath
    0.99
    <eos>
    0.95
     home
    0.88
    sprogramm
    0.87
    那时候
    0.85
     وكان
    0.85
     compaction
    0.85
    onade
    0.84
    Activations Density 0.001%

    No Known Activations