© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2040
    Prev
    Next
    INDEX
    Explanations

    technical and theoretical concepts

    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
    Послед
    0.36
    త్మిక
    0.35
     Dynkin
    0.34
     Ceux
    0.34
     Andrey
    0.34
    linalg
    0.34
    
    0.33
     системати
    0.33
    鹄
    0.33
     হস্তে
    0.32
    POSITIVE LOGITS
    تھی
    0.40
     सुमन
    0.38
     എസ്
    0.35
    ہد
    0.34
    են
    0.34
    ’
    0.33
    覀
    0.33
    Sea
    0.33
     एसडी
    0.33
     SB
    0.33
    Activations Density 0.150%

    No Known Activations