© 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. 23195
    Prev
    Next
    INDEX
    Explanations

    pipes and plumbing

    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
    涅
    0.39
     भिखारी
    0.37
    ابقات
    0.37
     demethyl
    0.37
    朵
    0.37
    靥
    0.37
    轲
    0.37
    钞
    0.36
     Faces
    0.35
    脱毛
    0.35
    POSITIVE LOGITS
     pipes
    2.83
     pipe
    2.70
     पाइप
    2.48
     Pipes
    2.44
    pipe
    2.42
     Pipe
    2.42
    Pipe
    2.38
    pipes
    2.36
     piping
    2.33
    管道
    2.19
    Activations Density 0.024%

    No Known Activations