© 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. 1097
    Prev
    Next
    INDEX
    Explanations

    Indonesian-Malay words followed by specific post-tokens

    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
     también
    -1.41
    ciless
    -1.36
    6
    -1.34
     InputMaybe
    -1.30
    𓂀
    -1.29
    țiuni
    -1.28
    likleri
    -1.28
     if
    -1.25
     eğer
    -1.24
     после
    -1.23
    POSITIVE LOGITS
    ?
    1.31
    بدأ
    1.30
     лишь
    1.30
     ...)
    1.28
    ?”
    1.28
     remain
    1.27
    ).”
    1.27
     bobina
    1.27
     лише
    1.27
     }
    1.26
    Activations Density 0.034%

    No Known Activations