© 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. 129882
    Prev
    Next
    INDEX
    Explanations

    questions or code context

    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
    oplast
    -0.06
    !
    -0.05
    :
    -0.05
    従来の
    -0.05
    <b>
    -0.05
    *
    -0.05
    पहले
    -0.05
    <strong>
    -0.05
     
    -0.05
     zunächst
    -0.05
    POSITIVE LOGITS
     კომპ
    0.07
     आंक
    0.07
     has
    0.07
     कु
    0.07
     zostało
    0.07
     sépar
    0.06
     BEL
    0.06
    แล้ว
    0.06
     ಅಗ
    0.06
     വര്‍
    0.06
    Activations Density 0.002%

    No Known Activations