© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117932
    Prev
    Next
    INDEX
    Explanations

    either...or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sebelum
    -0.06
     setelah
    -0.06
    after
    -0.06
     want
    -0.06
     например
    -0.06
     после
    -0.06
    比如
    -0.06
     loudness
    -0.06
    たとえば
    -0.06
     After
    -0.06
    POSITIVE LOGITS
     einzigen
    0.07
     erős
    0.05
     alimentação
    0.05
    čiau
    0.05
     एकमात्र
    0.05
     %@
    0.05
     লইয়
    0.05
     alimentación
    0.05
    źnie
    0.05
     keinen
    0.05
    Activations Density 0.035%

    No Known Activations