© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 13973
    Prev
    Next
    INDEX
    Explanations

    drinking water

    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
     старосног
    0.42
     ժ
    0.42
    邬
    0.40
     політи
    0.39
    𝐧
    0.39
    ApiKey
    0.39
    犯罪
    0.38
     क्रिप्टोकरेंसी
    0.38
     రే
    0.37
     राजनीतिक
    0.37
    POSITIVE LOGITS
     water
    3.11
    water
    2.69
    Water
    2.63
     Water
    2.61
    水
    2.56
     WATER
    2.52
     पानी
    2.48
     agua
    2.45
     água
    2.45
    水的
    2.44
    Activations Density 0.090%

    No Known Activations