© 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. 31-GEMMASCOPE-2-RES-262K
    7. 17488
    Prev
    Next
    INDEX
    Explanations

    UniFi builder syntax

    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_31_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
    setKeep
    0.39
    檩
    0.38
    ştur
    0.37
    dh
    0.36
     Brothers
    0.36
    ]*(
    0.36
    stown
    0.36
     fist
    0.36
    ববার
    0.36
     घरवालों
    0.35
    POSITIVE LOGITS
    分數
    0.40
     பகுதி
    0.40
     ذہنی
    0.39
     바꾸
    0.38
     від
    0.38
    SPORT
    0.37
     TBA
    0.37
    ፡
    0.37
     ora
    0.37
     cepat
    0.36
    Activations Density 0.000%

    No Known Activations