© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 180092
    Prev
    Next
    INDEX
    Explanations

    relationships with people

    np_acts-logits-general · gemini-2.5-flash-lite

    systems and failures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    reiche
    0.48
    츨
    0.47
     явления
    0.46
    Khud
    0.46
     Coxeter
    0.45
    lanan
    0.45
     NCBI
    0.45
    கார
    0.45
    лена
    0.44
    ্ব
    0.44
    POSITIVE LOGITS
     —
    0.53
     procure
    0.46
    。（
    0.45
     k
    0.45
     percent
    0.43
    imia
    0.43
     cầu
    0.43
     rigging
    0.43
     force
    0.42
     STP
    0.42
    Activations Density 0.001%

    No Known Activations