© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 16645
    Prev
    Next
    INDEX
    Explanations

    non-english characters in code

    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_262k_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
     categor
    1.22
     hypothes
    1.20
    e
    1.19
     scrutin
    1.13
    i
    1.13
     synthes
    1.09
     for
    1.06
     sanit
    1.06
    an
    1.05
    л
    1.05
    POSITIVE LOGITS
    ای
    1.16
    owane
    1.10
    า
    1.10
    owanie
    1.09
    ী
    1.06
     書い
    1.05
    एम
    1.02
    માં
    0.97
    لیت
    0.96
    ował
    0.96
    Activations Density 0.029%

    No Known Activations