© 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. 92627
    Prev
    Next
    INDEX
    Explanations

    horse ages two and three

    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
    ＝＝＝＝
    -0.93
     レビュー
    -0.93
    これまでの
    -0.84
    ないように
    -0.82
    穿搭
    -0.81
    哈哈哈哈
    -0.81
    素人
    -0.80
     famiglie
    -0.80
    そうで
    -0.79
    galeria
    -0.79
    POSITIVE LOGITS
    Gesture
    0.81
    설
    0.81
    τος
    0.81
    iorgio
    0.79
    Cond
    0.79
    masing
    0.79
    ณ
    0.79
    nasi
    0.78
    INVISIBLE
    0.78
    ActionMode
    0.78
    Activations Density 0.010%

    No Known Activations