© 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. 34-GEMMASCOPE-RES-131K
    7. 4148
    Prev
    Next
    INDEX
    Explanations

    what follows about

    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_34/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
    遑
    -1.46
     они
    -1.38
    )]$
    -1.34
    ⬈
    -1.32
    ).
    -1.32
    快要
    -1.30
     legislación
    -1.28
    ,
    -1.26
    跻
    -1.23
     使っ
    -1.23
    POSITIVE LOGITS
     how
    3.44
     what
    2.50
     the
    2.44
     why
    1.68
     where
    1.63
    如何
    1.61
     them
    1.60
     whether
    1.59
    为什么
    1.55
    Gdzie
    1.48
    Activations Density 0.062%

    No Known Activations