© 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. 107076
    Prev
    Next
    INDEX
    Explanations

    known as the July 4th

    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
    🤫
    -1.02
    ARCHIVE
    -0.86
    ❤️❤️❤️
    -0.85
    🌲
    -0.85
    💛
    -0.85
     ========
    -0.84
    ειτουργ
    -0.83
    DrawerLayout
    -0.81
    🤪
    -0.81
     rahasia
    -0.81
    POSITIVE LOGITS
     foray
    0.84
     advantages
    0.76
     verbund
    0.75
     struggle
    0.75
     thick
    0.74
    𝒽
    0.72
    做到
    0.72
     plumme
    0.72
     sauber
    0.71
     получили
    0.71
    Activations Density 0.011%

    No Known Activations