© 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. 230
    Prev
    Next
    INDEX
    Explanations

    about"}, "The"}, "Block"}, "Loan", "Features"}

    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
    伤感
    -1.18
    ֶּ
    -1.16
     учетом
    -1.15
    ceptable
    -1.13
     this
    -1.12
     sahaja
    -1.06
     съдържа
    -1.03
    bedingt
    -1.02
     it
    -1.01
    raujo
    -1.01
    POSITIVE LOGITS
     our
    1.38
     benefits
    1.23
     Our
    1.11
     nossos
    1.09
    Цели
    1.06
     fiquei
    1.05
     brochure
    1.02
     quidem
    1.02
     边框
    1.01
    ouching
    1.01
    Activations Density 0.008%

    No Known Activations