© 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. 221970
    Prev
    Next
    INDEX
    Explanations

    numbers close to zero

    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
    Pearson
    0.41
    El
    0.40
    Smith
    0.39
     trabalhar
    0.38
    multilayer
    0.38
    晃
    0.38
    eref
    0.38
    勃
    0.38
    Exhibit
    0.38
    Appendix
    0.37
    POSITIVE LOGITS
     brute
    0.40
     대부분
    0.38
     большинства
    0.37
     grosso
    0.37
     Lyn
    0.36
    tif
    0.35
     इसको
    0.35
     Quincy
    0.35
     Precis
    0.35
     bail
    0.35
    Activations Density 0.030%

    No Known Activations