© 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. 22-GEMMASCOPE-RES-131K
    7. 68167
    Prev
    Next
    INDEX
    Explanations

    and pronoun

    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_22/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
     yaptığı
    -1.04
     is
    -0.98
     its
    -0.88
     kendini
    -0.86
    licopter
    -0.83
    以上
    -0.82
     greeted
    -0.81
    wasn
    -0.81
    luents
    -0.79
    igsaw
    -0.79
    POSITIVE LOGITS
     my
    1.37
     together
    1.23
     mutually
    1.20
     mutual
    1.16
     they
    1.14
     their
    1.12
     I
    1.06
    กัน
    1.03
     έχουν
    1.02
     juntos
    1.02
    Activations Density 0.073%

    No Known Activations