© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49824
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming language keywords

    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
    their
    -1.45
    他們
    -1.41
    쐈
    -1.37
     mété
    -1.33
    他们的
    -1.31
    雠
    -1.30
     seront
    -1.28
     maniere
    -1.27
    Keine
    -1.27
    他们
    -1.27
    POSITIVE LOGITS
     in
    1.55
     as
    1.38
     For
    1.30
     With
    1.29
     to
    1.22
     As
    1.20
     Even
    1.20
     There
    1.18
     At
    1.18
     What
    1.17
    Activations Density 0.011%

    No Known Activations