© 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. 11030
    Prev
    Next
    INDEX
    Explanations

    inductance and inductors

    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
     was
    -1.52
     volks
    -1.43
     frau
    -1.37
    plication
    -1.35
     chansons
    -1.32
     volk
    -1.32
    镦
    -1.30
    %,
    -1.30
     restau
    -1.29
     traduction
    -1.27
    POSITIVE LOGITS
     nadzieję
    1.47
     หรือ
    1.41
     jūs
    1.40
    فية
    1.38
     jums
    1.37
    ナの
    1.34
     ewigen
    1.33
     povezave
    1.30
     actualización
    1.28
     esferas
    1.28
    Activations Density 0.032%

    No Known Activations