© 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. 14116
    Prev
    Next
    INDEX
    Explanations

    Quranic verses and Islamic concepts

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

    Quranic verses and references

    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
    িনবার্গ
    0.52
    ፌ
    0.52
    Aging
    0.51
     سینٹی
    0.51
     mój
    0.49
    itchfield
    0.48
     recevoir
    0.48
     źród
    0.48
    zięki
    0.48
    ጬ
    0.47
    POSITIVE LOGITS
     Quran
    0.53
     menjadikan
    0.53
     sebagai
    0.50
    adikan
    0.49
     Islamic
    0.49
    adiya
    0.49
     menjaga
    0.48
     dijadikan
    0.48
     Penelitian
    0.47
     Muslim
    0.46
    Activations Density 0.016%

    No Known Activations