© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 166888
    Prev
    Next
    INDEX
    Explanations

    temperature and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cervantes
    0.41
    賁
    0.41
     пове
    0.38
    贲
    0.38
    Lincoln
    0.38
    జే
    0.37
     कैल्शियम
    0.36
    脇
    0.36
     सर्वात
    0.36
     種
    0.36
    POSITIVE LOGITS
     Dong
    0.41
     dong
    0.40
     défaut
    0.39
     namesake
    0.38
     formación
    0.38
     subdir
    0.38
     nr
    0.38
     gezegd
    0.37
     intégral
    0.37
     Nr
    0.37
    Activations Density 0.000%

    No Known Activations