© 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-262K
    7. 221782
    Prev
    Next
    INDEX
    Explanations

    descriptive abstract terms

    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
    优化
    0.47
    娀
    0.39
    裔
    0.39
    獗
    0.38
    नाडा
    0.37
     प्रतिबद्ध
    0.37
    攜
    0.37
    definition
    0.37
    栊
    0.37
     বো
    0.36
    POSITIVE LOGITS
     unlink
    0.41
     contemplating
    0.41
     banknote
    0.41
     mok
    0.41
     progreso
    0.40
     máquina
    0.40
     concerts
    0.40
     Gemä
    0.40
     concert
    0.39
     člove
    0.39
    Activations Density 0.000%

    No Known Activations