© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30519
    Prev
    Next
    INDEX
    Explanations

    academic names and citations

    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
     then
    -0.82
     reliable
    -0.80
    站点
    -0.79
    蕭
    -0.78
     proved
    -0.78
     dose
    -0.77
     Dobson
    -0.75
     wouldnt
    -0.75
     failed
    -0.74
     helped
    -0.74
    POSITIVE LOGITS
     EFT
    0.99
    žiaga
    0.91
    PHYSICAL
    0.91
    PreExecute
    0.90
     PTE
    0.87
    Guardians
    0.86
    Bitcoin
    0.85
     arrang
    0.85
     infographic
    0.85
    constexpr
    0.85
    Activations Density 0.045%

    No Known Activations