© 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. 57054
    Prev
    Next
    INDEX
    Explanations

    shipping carriers

    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
     infall
    0.47
     isometry
    0.47
    llo
    0.47
    t
    0.47
     মেয়েটি
    0.45
     excellently
    0.45
     মানবতার
    0.45
    srcset
    0.44
     दुल्हन
    0.43
    ⇅
    0.43
    POSITIVE LOGITS
     wash
    0.49
     Houses
    0.48
     الأ
    0.44
     Adams
    0.43
     perju
    0.42
     of
    0.42
     الصح
    0.42
     share
    0.41
     HIGH
    0.41
     semakin
    0.41
    Activations Density 0.017%

    No Known Activations