© 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. 187544
    Prev
    Next
    INDEX
    Explanations

    or / either / alternatives

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

    "or" variations

    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
     सलाहकार
    0.48
     Pharmacology
    0.46
     Materials
    0.46
     Remedies
    0.45
     sebagaimana
    0.45
    깼
    0.44
    Suspend
    0.44
    සු
    0.44
     Petroleum
    0.43
     tahu
    0.42
    POSITIVE LOGITS
    或者
    0.61
     ឬ
    0.59
     oder
    0.58
     или
    0.58
    或
    0.57
     or
    0.54
    もしくは
    0.54
     或者
    0.54
     hoặc
    0.54
    หรือ
    0.54
    Activations Density 0.004%

    No Known Activations