© 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. 118036
    Prev
    Next
    INDEX
    Explanations

    unknown origin or reason

    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
     its
    -0.06
    它的
    -0.06
     ligação
    -0.06
    その
    -0.06
     系统
    -0.06
     njegov
    -0.06
    ；
    -0.06
     específicos
    -0.05
     diagnosis
    -0.05
     precedents
    -0.05
    POSITIVE LOGITS
     on
    0.08
     with
    0.07
     for
    0.06
     гораздо
    0.06
     my
    0.06
     इन्हीं
    0.06
     যদিও
    0.06
    সাধারণ
    0.06
    雖然
    0.06
     बेशक
    0.06
    Activations Density 0.012%

    No Known Activations