© 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
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 20329
    Prev
    Next
    INDEX
    Explanations

    table and things on it

    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_53_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
     hanging
    0.43
     cay
    0.41
    杓
    0.40
     tube
    0.39
     hadron
    0.38
    浣
    0.38
    门口
    0.38
    eston
    0.37
    管道
    0.37
    agamo
    0.37
    POSITIVE LOGITS
    cloth
    0.95
     tablecloth
    0.82
    tennis
    0.77
     テーブル
    0.70
     cloths
    0.69
    桌
    0.68
    Table
    0.67
     ITable
    0.67
     tabletop
    0.66
     cloth
    0.65
    Activations Density 0.020%

    No Known Activations