© 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. 40-GEMMASCOPE-2-RES-262K
    7. 224805
    Prev
    Next
    INDEX
    Explanations

    redundancy

    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
    green
    0.61
     greenish
    0.59
     রঙের
    0.58
     green
    0.57
     yellow
    0.54
    色的
    0.54
    Green
    0.52
    색
    0.52
    绿
    0.52
     orange
    0.50
    POSITIVE LOGITS
    redund
    0.49
    การณ์
    0.47
    芑
    0.45
     redund
    0.45
    aidh
    0.45
     redeem
    0.44
     معاش
    0.44
     redundant
    0.43
     redundancies
    0.43
    拶
    0.42
    Activations Density 0.020%

    No Known Activations