© 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. 22-GEMMASCOPE-RES-131K
    7. 68060
    Prev
    Next
    INDEX
    Explanations

    Nevanlinna-Pick interpolation

    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
     vacía
    -1.23
    為に
    -1.22
    ことで
    -1.16
     alza
    -1.16
    事で
    -1.16
    ビックリ
    -1.14
     anlay
    -1.11
     nour
    -1.10
    stunning
    -1.10
     morta
    -1.09
    POSITIVE LOGITS
     Redewendung
    1.16
    思います
    1.15
     zestawie
    1.13
     ozdob
    1.12
    Jereo
    1.09
    mohon
    1.09
    مشخصات
    1.08
    ｪ
    1.08
     vestito
    1.05
     kartą
    1.04
    Activations Density 0.130%

    No Known Activations