© 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. 175749
    Prev
    Next
    INDEX
    Explanations

    Islamic prayers and permissions

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

    subject-predicate-object triplets

    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
    માં
    0.50
     Linux
    0.49
     linux
    0.46
    ＊
    0.46
    ለያዩ
    0.45
    焦点
    0.44
    BDF
    0.44
     Foire
    0.43
    wb
    0.43
     piatta
    0.43
    POSITIVE LOGITS
    <0xA1>
    0.53
    ionalmente
    0.45
    its
    0.43
    țiilor
    0.43
    طف
    0.42
    ión
    0.41
     reverence
    0.41
    aturally
    0.41
    ational
    0.40
    不如
    0.40
    Activations Density 0.005%

    No Known Activations