© 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. 95508
    Prev
    Next
    INDEX
    Explanations

    offers and guarantees

    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
    ícias
    -1.48
     other
    -1.29
    ceptable
    -1.16
    mountable
    -1.10
    indahkan
    -1.09
    えると
    -1.09
     съдържа
    -1.08
    ဤ
    -1.07
    arschijnlijk
    -1.07
    ائية
    -1.04
    POSITIVE LOGITS
     guarantee
    1.48
     hassle
    1.38
     service
    1.36
     support
    1.36
     you
    1.27
     secure
    1.27
     user
    1.22
     bát
    1.20
     guarantees
    1.20
     dessutom
    1.18
    Activations Density 0.045%

    No Known Activations