© 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. 10-GEMMASCOPE-RES-131K
    4. 48364
    Prev
    Next
    INDEX
    Explanations

    vehicles and conditions

    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_10/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
    ຣ
    -1.41
    会う
    -1.37
    可谓
    -1.35
    缜
    -1.34
    際の
    -1.29
     by
    -1.28
    一时间
    -1.27
     from
    -1.27
    ־ה
    -1.27
     Suiza
    -1.26
    POSITIVE LOGITS
     you
    1.45
     Erzb
    1.32
     your
    1.24
    shadowRadius
    1.23
    /*
    1.21
     утеп
    1.20
     برای
    1.20
    bangun
    1.17
     картофе
    1.17
    diye
    1.16
    Activations Density 0.138%

    No Known Activations