© 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. 12329
    Prev
    Next
    INDEX
    Explanations

    specific surnames and places

    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
    ⌥
    -2.52
    并且
    -2.44
    涠
    -2.39
    🪬
    -2.34
    tiler
    -2.31
    说是
    -2.31
     незавер
    -2.30
    ﻒ
    -2.30
    OSPITAL
    -2.25
    鹇
    -2.25
    POSITIVE LOGITS
     The
    3.13
    h
    2.97
    j
    2.77
    ers
    2.67
    ll
    2.66
    当下
    2.63
            
    2.56
    tt
    2.53
     Comes
    2.47
     MOST
    2.42
    Activations Density 0.031%

    No Known Activations