© 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. 13666
    Prev
    Next
    INDEX
    Explanations

    code directives

    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
     their
    -1.52
     its
    -1.50
     it
    -1.27
     other
    -1.20
    ȴ
    -1.19
     this
    -1.17
    耳机
    -1.15
    行きたい
    -1.13
     those
    -1.12
     thier
    -1.09
    POSITIVE LOGITS
    星人
    1.28
     ")");
    1.28
    耵
    1.27
     penulis
    1.23
    所有
    1.21
    legungen
    1.20
    ovu
    1.20
    ге
    1.19
    blé
    1.18
    新型
    1.17
    Activations Density 0.000%

    No Known Activations