© 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. 31-GEMMASCOPE-2-RES-262K
    7. 4755
    Prev
    Next
    INDEX
    Explanations

    one entity to another

    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_31_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
    Show
    0.40
    Actual
    0.39
    internal
    0.37
    延
    0.35
     “
    0.34
    Action
    0.34
    Elev
    0.34
    虚
    0.34
     Mellon
    0.33
    CV
    0.33
    POSITIVE LOGITS
     spesso
    0.53
     mudah
    0.48
    鵃
    0.46
     empresas
    0.45
    ellikle
    0.44
    blusas
    0.44
     geralmente
    0.43
     mehrerer
    0.43
     embarazada
    0.42
    рани
    0.41
    Activations Density 0.001%

    No Known Activations