© 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. 120396
    Prev
    Next
    INDEX
    Explanations

    calling upon god

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

    Arabic names and words

    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
    措
    0.49
    ника
    0.46
     substrates
    0.45
     quotas
    0.44
     fasteners
    0.43
     normes
    0.42
    imiento
    0.42
    ื่อ
    0.41
    мой
    0.41
    頜
    0.41
    POSITIVE LOGITS
     allah
    0.53
     Mubarak
    0.50
     Wadi
    0.50
     Allah
    0.48
     Arik
    0.48
     Funeral
    0.47
     Multif
    0.47
    阿拉
    0.47
     असंख्य
    0.46
    Allah
    0.46
    Activations Density 0.002%

    No Known Activations