© 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. 10-GEMMASCOPE-RES-131K
    7. 124633
    Prev
    Next
    INDEX
    Explanations

    relation to

    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
    糨
    -1.28
        
    -1.20
     träd
    -1.17
    成了
    -1.16
     skydd
    -1.14
     россия
    -1.14
     zimní
    -1.13
     kovo
    -1.10
    𝚋
    -1.10
     země
    -1.09
    POSITIVE LOGITS
     sorprender
    1.29
    tamientos
    1.28
    ﺕ
    1.23
     renov
    1.21
     или
    1.20
     даже
    1.19
    getreten
    1.16
    اقرأ
    1.16
    valg
    1.15
     soulign
    1.15
    Activations Density 0.852%

    No Known Activations