© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71641
    Prev
    Next
    INDEX
    Explanations

    Spark followed by technical 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
    ↵
    -2.95
    秝
    -2.77
    嫫
    -2.39
    馘
    -2.34
     scared
    -2.17
    铙
    -2.14
    栳
    -2.11
    猡
    -2.09
     sustaining
    -2.08
    杁
    -2.08
    POSITIVE LOGITS
     Если
    2.36
     Когда
    2.31
    archiwizowane
    2.30
    笮
    2.23
     皮肤
    2.20
    ということで
    2.19
     είναι
    2.17
    ZZLE
    2.14
    她的
    2.13
    窳
    2.11
    Activations Density 0.004%

    No Known Activations