© 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-16K
    7. 8835
    Prev
    Next
    INDEX
    Explanations

    wires diagram nodes category

    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_16k_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
    spinlock
    0.45
     econômica
    0.42
    exclusions
    0.40
     ನಾಗ
    0.40
     pore
    0.38
    exclusion
    0.38
    纮
    0.38
     tit
    0.38
     தொற்று
    0.38
    洸
    0.37
    POSITIVE LOGITS
    涧
    0.44
     wires
    0.44
     Category
    0.41
     Node
    0.41
    射
    0.41
    Aware
    0.40
    wires
    0.40
    Diagram
    0.40
    Category
    0.40
    Wires
    0.40
    Activations Density 0.030%

    No Known Activations