© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129506
    Prev
    Next
    INDEX
    Explanations

    addresses and locations

    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
     and
    -1.37
     belangrijk
    -1.14
     to
    -1.09
     that
    -1.06
    ほら
    -1.02
    恙
    -1.02
    んだろう
    -1.00
    बस
    -0.96
    ようになりました
    -0.96
    ッタ
    -0.96
    POSITIVE LOGITS
     بسیار
    1.10
    とはいえ
    1.09
     Pristup
    1.07
    嗐
    1.06
    があり
    1.05
    Dziękuję
    1.05
    方針
    1.05
    واقع
    1.04
    髋
    1.02
     Mã
    1.01
    Activations Density 0.011%

    No Known Activations