© 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. 17663
    Prev
    Next
    INDEX
    Explanations

    extract description

    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
    ⅼ
    0.17
     Много
    0.15
    <unused2155>
    0.15
    doing
    0.15
     কিন্ত
    0.15
    defin
    0.15
    但是在
    0.15
    }$.
    0.15
     канторы
    0.15
    osta
    0.14
    POSITIVE LOGITS
     Python
    0.16
     Verlet
    0.16
     adimensional
    0.16
     python
    0.15
     Jimin
    0.15
     protein
    0.14
     ghi
    0.14
     inode
    0.14
     lésions
    0.14
     ich
    0.14
    Activations Density 0.000%

    No Known Activations