© 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. 34-GEMMASCOPE-RES-131K
    7. 54127
    Prev
    Next
    INDEX
    Explanations

    URL, code, and technical descriptions

    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
     until
    -0.93
     Muster
    -0.91
    dedor
    -0.91
     ليب
    -0.88
    منى
    -0.88
     desorption
    -0.87
     mī
    -0.84
    ғ
    -0.81
    рованного
    -0.80
     Messung
    -0.79
    POSITIVE LOGITS
     (?)
    0.91
     THERE
    0.88
    하지
    0.85
    wasn
    0.84
     manteiga
    0.82
    ├──
    0.81
    cher
    0.81
    chal
    0.81
     Hmm
    0.81
     onResume
    0.80
    Activations Density 0.002%

    No Known Activations