© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54392
    Prev
    Next
    INDEX
    Explanations

    Azure DevOps connections

    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_65k_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
     ܠ
    0.42
     उप
    0.39
    langle
    0.38
     slums
    0.38
     kome
    0.38
    Commit
    0.37
    berg
    0.36
    lens
    0.36
    Launched
    0.36
    <tbody>
    0.36
    POSITIVE LOGITS
    Picklist
    0.47
     variabile
    0.46
    Tarefa
    0.45
    тр
    0.44
     टास्क
    0.41
     variables
    0.41
    叄
    0.41
     Qxa
    0.40
     tarefas
    0.40
     task
    0.40
    Activations Density 0.011%

    No Known Activations