© 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. 11263
    Prev
    Next
    INDEX
    Explanations

    creating or implementing actions

    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
     this
    -1.85
     these
    -1.63
    ignment
    -1.49
     چنین
    -1.45
    iric
    -1.45
     it
    -1.44
     スイッチ
    -1.41
    itisation
    -1.38
    justed
    -1.38
    ícias
    -1.38
    POSITIVE LOGITS
     даже
    1.25
    <>
    1.23
     років
    1.20
     конструкция
    1.20
     O
    1.19
     mivel
    1.19
    1.18
     практика
    1.17
     всего
    1.16
     >
    1.15
    Activations Density 0.049%

    No Known Activations