© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 244454
    Prev
    Next
    INDEX
    Explanations

    online efforts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ஓம்
    0.52
    𝘬
    0.52
    Categ
    0.49
     катего
    0.49
    Omar
    0.49
    Woo
    0.49
     এঁ
    0.48
     র
    0.47
    שא
    0.47
     ом
    0.47
    POSITIVE LOGITS
     conclusive
    0.52
     space
    0.52
     sophisticated
    0.52
     a
    0.52
     reproduced
    0.50
     developed
    0.50
     document
    0.49
     syndicated
    0.48
     regulation
    0.48
     conductance
    0.48
    Activations Density 0.000%

    No Known Activations