© 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. 222699
    Prev
    Next
    INDEX
    Explanations

    seeking script

    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
     이날
    0.40
    strahlung
    0.38
    个
    0.38
    visually
    0.37
     inlets
    0.36
    Distance
    0.36
    йте
    0.35
     बृहस्पतिवार
    0.35
    দৃষ্টি
    0.35
     पीएफआई
    0.35
    POSITIVE LOGITS
    ('+
    0.44
    ქ
    0.42
     заво
    0.39
     कस्टम
    0.38
     inducing
    0.37
     Nava
    0.37
    ខ្
    0.36
    luss
    0.35
     corruption
    0.35
     quiso
    0.35
    Activations Density 0.007%

    No Known Activations