© 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. 41-GEMMASCOPE-2-RES-262K
    7. 65347
    Prev
    Next
    INDEX
    Explanations

    conjunctions followed by clauses

    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_all/layer_41_width_262k_l0_big
    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
    اليا
    0.45
    λαβ
    0.42
    ение
    0.40
    اید
    0.39
     Ask
    0.37
     kys
    0.37
    シリ
    0.36
    뎐
    0.36
    წყვე
    0.36
     εμφ
    0.36
    POSITIVE LOGITS
    after
    1.15
     after
    1.13
     setelah
    1.13
    After
    1.13
    经过
    1.06
     After
    1.05
     после
    1.03
     después
    1.01
     dopo
    1.01
     após
    1.00
    Activations Density 0.000%

    No Known Activations