© 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. 26013
    Prev
    Next
    INDEX
    Explanations

    method calls

    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
     When
    -1.45
     While
    -1.35
     Every
    -1.32
     Each
    -1.27
     with
    -1.27
     and
    -1.27
     These
    -1.23
     these
    -1.23
    寳
    -1.21
     וכן
    -1.16
    POSITIVE LOGITS
    ↵
    1.55
     kılıf
    1.27
    doc
    1.22
     applau
    1.22
    粜
    1.18
    trying
    1.16
    纐
    1.12
    dont
    1.11
    shall
    1.10
     yeter
    1.10
    Activations Density 0.006%

    No Known Activations