© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 162639
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns

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

    novel combinations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     తిరిగి
    0.48
    নতুন
    0.46
    ﾛ
    0.45
    ᱨ
    0.44
    फी
    0.43
     নতুন
    0.43
     benefiting
    0.43
    ོ
    0.43
     derniers
    0.42
     edildi
    0.42
    POSITIVE LOGITS
     этих
    0.66
     this
    0.61
     эту
    0.57
     these
    0.57
     эти
    0.55
    this
    0.52
     этой
    0.51
     этого
    0.50
     этот
    0.49
     هذا
    0.49
    Activations Density 0.001%

    No Known Activations