© 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-65K
    7. 15828
    Prev
    Next
    INDEX
    Explanations

    tissue located

    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_65k_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
     ใคร
    0.45
     estamp
    0.44
     begs
    0.43
     עצ
    0.42
     მ
    0.41
     vanishes
    0.40
    これで
    0.40
     경쟁
    0.39
     जादू
    0.39
     विफल
    0.39
    POSITIVE LOGITS
     ;\
    0.43
     torr
    0.43
     werden
    0.42
    čných
    0.42
     olmasına
    0.42
    вих
    0.41
    water
    0.40
    voltage
    0.40
     utilizzare
    0.40
     UpdateWindow
    0.40
    Activations Density 0.011%

    No Known Activations