© 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. 28021
    Prev
    Next
    INDEX
    Explanations

    specialized terms

    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
     both
    -1.70
     these
    -1.65
     and
    -1.52
     only
    -1.48
     those
    -1.33
     also
    -1.21
    fordshire
    -1.17
     zowel
    -1.16
     mainly
    -1.13
     sowohl
    -1.13
    POSITIVE LOGITS
     czasem
    1.30
    えっ
    1.16
    んですよね
    1.16
     aiment
    1.16
    着头
    1.16
     sienta
    1.16
     cérami
    1.14
    𝟏
    1.13
     chirurgie
    1.13
    ∅
    1.13
    Activations Density 0.066%

    No Known Activations