© 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. 164738
    Prev
    Next
    INDEX
    Explanations

    botox | days | locations

    np_acts-logits-general · gemini-2.5-flash-lite

    historical, scientific, or foundational concepts

    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
    امل
    0.46
    洍
    0.46
    层的
    0.46
    昷
    0.46
    θη
    0.45
     هذا
    0.45
     жало
    0.44
    层
    0.44
    但这
    0.43
     precedente
    0.43
    POSITIVE LOGITS
    0
    0.46
    );
    0.45
     United
    0.45
     professional
    0.45
     scientist
    0.45
     \
    0.44
    professional
    0.44
     trainee
    0.43
     Ngh
    0.43
    ";//
    0.42
    Activations Density 0.000%

    No Known Activations