© 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. 31-GEMMASCOPE-2-RES-262K
    7. 6317
    Prev
    Next
    INDEX
    Explanations

    solving equations

    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_31_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
     densément
    0.37
     communautés
    0.37
     acteurs
    0.36
    陼
    0.36
    තිය
    0.36
     memória
    0.36
    زش
    0.35
     tarses
    0.35
     civile
    0.35
     comté
    0.35
    POSITIVE LOGITS
     equation
    0.55
    Equation
    0.55
     Equation
    0.50
    equation
    0.48
    ↵
    0.48
     equations
    0.48
     Equations
    0.44
     equação
    0.42
     equate
    0.39
    forcing
    0.37
    Activations Density 0.150%

    No Known Activations