© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63017
    Prev
    Next
    INDEX
    Explanations

    Shi/时/Cyrillic S initial syllables

    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_34/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
    ネマ
    -0.85
    caris
    -0.82
     excused
    -0.81
    unción
    -0.80
    ́ng
    -0.79
     pylint
    -0.78
    žia
    -0.78
    hydrogenase
    -0.77
    간
    -0.75
    ươi
    -0.74
    POSITIVE LOGITS
     시
    0.83
    MINUTES
    0.81
    atief
    0.79
    Ṁ
    0.77
     relevant
    0.74
    的角度
    0.74
    Held
    0.72
     commonly
    0.72
     Oft
    0.72
     common
    0.71
    Activations Density 0.002%

    No Known Activations