© 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. 100562
    Prev
    Next
    INDEX
    Explanations

    justice, fairness, integrity, Facebook

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

    business terms

    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
    そして
    0.60
    math
    0.50
    u
    0.50
    spiration
    0.49
     relentless
    0.48
     relentlessly
    0.46
    et
    0.44
     आणि
    0.44
    widehat
    0.43
    ç
    0.42
    POSITIVE LOGITS
     或
    0.66
     или
    0.61
    或
    0.59
     alebo
    0.57
    或其他
    0.52
    หรือ
    0.51
     veya
    0.47
     ወይም
    0.47
     койма
    0.47
     Asalamualaikum
    0.46
    Activations Density 0.002%

    No Known Activations