Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11634
    Prev
    Next
    INDEX
    Explanations

    in front of

    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_22/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
    </b>
    -2.17
     acoged
    -2.13
     schein
    -2.02
     unglaub
    -1.96
     different
    -1.88
    ありますか
    -1.87
     cómoda
    -1.85
     merkwür
    -1.85
    偌
    -1.84
    ありますが
    -1.78
    POSITIVE LOGITS
     of
    7.28
     Главная
    2.09
     折り
    2.02
     juſt
    1.99
    ним
    1.97
     apparaissent
    1.89
    提到
    1.88
    zellen
    1.86
     Hinblick
    1.84
     étoile
    1.84
    Activations Density 0.033%

    No Known Activations