© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 848
    Prev
    Next
    INDEX
    Explanations

    doing nothing

    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_16_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
     which
    0.66
     parchment
    0.64
    р
    0.64
     four
    0.64
     three
    0.61
     chacune
    0.59
     human
    0.59
     formative
    0.58
     heres
    0.58
     tripartite
    0.58
    POSITIVE LOGITS
    तिथि
    0.58
     избежать
    0.56
     سريع
    0.55
    ↵↵↵
    0.54
    يمة
    0.54
    也会
    0.53
    ↵↵
    0.53
    ଓ
    0.53
     نفسك
    0.52
     వెంటనే
    0.51
    Activations Density 0.042%

    No Known Activations