© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117455
    Prev
    Next
    INDEX
    Explanations

    copyright, Authors, begin, Id, xaml

    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
    是
    -0.06
     therefore
    -0.06
    ุป
    -0.06
     volgens
    -0.06
     refers
    -0.06
     поэтому
    -0.06
    因此
    -0.06
     gestione
    -0.06
    )(
    -0.06
     செல்லும்
    -0.06
    POSITIVE LOGITS
    arı
    0.07
     compréhension
    0.06
     zostało
    0.06
    все
    0.06
     】,
    0.06
    졌다
    0.06
     skar
    0.06
    Finland
    0.06
     definitivamente
    0.06
     ;(
    0.06
    Activations Density 0.004%

    No Known Activations