© 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. 222450
    Prev
    Next
    INDEX
    Explanations

    waterproof

    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
     pred
    0.44
     jej
    0.42
     adsorbed
    0.42
    r
    0.41
     admitted
    0.40
    i
    0.39
    pred
    0.38
     scenes
    0.38
     limpi
    0.38
     "-",
    0.38
    POSITIVE LOGITS
    emento
    0.48
    疑惑
    0.43
    味料
    0.43
    ęła
    0.43
    人口
    0.42
    栯
    0.42
    তলা
    0.41
    百家乐
    0.41
    úsica
    0.41
    这份
    0.41
    Activations Density 0.010%

    No Known Activations