© 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. 31-GEMMASCOPE-2-RES-65K
    7. 47666
    Prev
    Next
    INDEX
    Explanations

    official, direct, not, traditions

    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
     this
    0.46
    meet
    0.45
     meet
    0.43
    reti
    0.43
     questa
    0.42
    梅
    0.42
     appear
    0.42
     ezt
    0.42
    ↵↵
    0.42
     هذا
    0.41
    POSITIVE LOGITS
     Kilometer
    0.48
    వె
    0.48
    jaty
    0.47
     Cable
    0.46
     enhancements
    0.46
     "=
    0.46
    되는
    0.46
    ث
    0.45
    atthaya
    0.45
     incubating
    0.45
    Activations Density 0.011%

    No Known Activations