© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33153
    Prev
    Next
    INDEX
    Explanations

    numbered sections or headings

    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
    detto
    -0.88
    kologi
    -0.84
    allinen
    -0.81
    limus
    -0.78
    Doc
    -0.78
     silo
    -0.77
    धन
    -0.77
    ᅠ
    -0.76
    niego
    -0.76
     cuer
    -0.76
    POSITIVE LOGITS
    ubmit
    0.84
     again
    0.82
    继续
    0.81
    bolsa
    0.79
    Ting
    0.76
    ーと
    0.76
     produrre
    0.72
    kespea
    0.71
    ビタミン
    0.71
     continue
    0.71
    Activations Density 0.000%

    No Known Activations