© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 192948
    Prev
    Next
    INDEX
    Explanations

    non-alcoholic beverages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    чан
    0.47
    сцю
    0.43
     crooked
    0.42
    Copyright
    0.37
     stray
    0.37
    篓
    0.36
     सियासी
    0.36
     शक
    0.35
    ヨン
    0.35
    容量
    0.35
    POSITIVE LOGITS
     mock
    0.70
     Mock
    0.69
     non
    0.66
     غير
    0.65
     Non
    0.64
    零
    0.63
     zero
    0.63
     sober
    0.63
    non
    0.60
    Non
    0.60
    Activations Density 0.024%

    No Known Activations