© 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. 2543
    Prev
    Next
    INDEX
    Explanations

    Na Zha

    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
     Ку
    -0.92
    ෂ
    -0.84
     Baş
    -0.83
     Kı
    -0.81
    oterapia
    -0.80
     mocht
    -0.79
    鑑賞
    -0.77
     Ба
    -0.77
    としての
    -0.76
    轰隆
    -0.75
    POSITIVE LOGITS
    斯
    0.93
    سون
    0.88
     映画
    0.87
    徳
    0.87
     خلف
    0.84
    表面
    0.82
    VARCHAR
    0.82
    氏
    0.80
    internalType
    0.79
    ceptives
    0.79
    Activations Density 0.005%

    No Known Activations