© 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. 10-GEMMASCOPE-RES-131K
    7. 66679
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and symbols

    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_10/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
     to
    -1.78
     and
    -1.50
     seguenti
    -1.43
     teolog
    -1.34
    ῖν
    -1.29
    兩
    -1.23
    とき
    -1.23
     نقط
    -1.22
     télévis
    -1.22
     esterni
    -1.21
    POSITIVE LOGITS
     côtes
    1.76
     poches
    1.71
    しゃれ
    1.50
    ּוֹ
    1.45
    了个
    1.45
     concepto
    1.45
    iteiten
    1.44
     segunda
    1.41
     durante
    1.41
     vœux
    1.41
    Activations Density 0.014%

    No Known Activations