© 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. 122837
    Prev
    Next
    INDEX
    Explanations

    clinical physiological

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

    Mom or building materials

    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
    ந்தது
    0.47
    ारा
    0.46
    ่วย
    0.44
    𝖔
    0.43
     Beirut
    0.42
     Vertrag
    0.42
     Bragg
    0.41
    IG
    0.40
     Dhaka
    0.40
     diharapkan
    0.40
    POSITIVE LOGITS
     سیر
    0.46
    ='
    0.45
    δυ
    0.44
     მონ
    0.44
    clinical
    0.43
    μορφ
    0.43
     اطلاعات
    0.43
    physiological
    0.43
     عد
    0.43
    これは
    0.43
    Activations Density 0.000%

    No Known Activations