© 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. 153689
    Prev
    Next
    INDEX
    Explanations

    conditions and relationships

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

    Quran mentions and associated concepts

    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
    데
    0.49
    violin
    0.49
    nissen
    0.48
     چھوٹ
    0.48
    ribusi
    0.47
    ਰਾ
    0.47
    ʒ
    0.47
     다섯
    0.45
    tls
    0.45
    hlas
    0.45
    POSITIVE LOGITS
     expedite
    0.48
     frequent
    0.48
    प्तान
    0.48
     won
    0.46
     komp
    0.46
     willing
    0.44
     तेज
    0.44
     fervent
    0.43
     ing
    0.43
     gave
    0.43
    Activations Density 0.000%

    No Known Activations