© 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. 80003
    Prev
    Next
    INDEX
    Explanations

    or usually

    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
    έ
    -1.20
    ί
    -1.20
    ό
    -1.19
    FileDescriptor
    -1.18
    ּוֹ
    -1.16
    フォーマンス
    -1.15
     überweisen
    -1.14
    不由得
    -1.13
     целый
    -1.12
    formatics
    -1.10
    POSITIVE LOGITS
     or
    1.86
    或者
    1.69
     либо
    1.63
    Usually
    1.58
     usually
    1.58
     Usually
    1.56
     или
    1.55
     обычно
    1.48
     suele
    1.48
    通常
    1.46
    Activations Density 0.049%

    No Known Activations