© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9770
    Prev
    Next
    INDEX
    Explanations

    Middleton, Dirk, Universität, Chinese, DropDownList

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    轳
    -3.28
    >
    -3.19
    着了
    -2.52
    にい
    -2.19
     plunged
    -2.19
    前方
    -2.17
    下に
    -2.17
     endured
    -2.17
    人
    -2.13
     desenvolver
    -2.08
    POSITIVE LOGITS
    d
    4.44
    翾
    3.48
    the
    3.05
    n
    2.97
    蚡
    2.72
    
    2.63
    
    2.55
    䊏
    2.55
    these
    2.53
    ୮
    2.52
    Activations Density 0.002%

    No Known Activations