© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 222697
    Prev
    Next
    INDEX
    Explanations

    adverbs qualifying actions or states

    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
    Std
    0.40
    WATER
    0.40
     त्यांचे
    0.40
     NT
    0.38
    ;'
    0.38
    逈
    0.37
     solns
    0.37
     ನೀರಿನ
    0.37
     Std
    0.37
     যের
    0.36
    POSITIVE LOGITS
    每个
    0.43
    每個
    0.42
     compren
    0.39
     ausschließlich
    0.39
    撷
    0.39
    ्म
    0.39
    عان
    0.39
    iseaux
    0.38
    嘖
    0.38
     hebdom
    0.38
    Activations Density 0.000%

    No Known Activations