© 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. 19433
    Prev
    Next
    INDEX
    Explanations

    camel case and capitalization

    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
    .",
    -1.42
    。
    -1.23
    ",
    -1.20
    sivité
    -1.20
    ",
    -1.19
    ',
    -1.19
    esi
    -1.15
     remedy
    -1.13
    ↵↵↵
    -1.10
    .</
    -1.09
    POSITIVE LOGITS
     this
    1.51
     partire
    1.31
     should
    1.28
     diverso
    1.26
     должны
    1.25
     männer
    1.23
     trebuie
    1.20
    citos
    1.20
    日起
    1.16
    ificação
    1.16
    Activations Density 0.029%

    No Known Activations