© 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. 116971
    Prev
    Next
    INDEX
    Explanations

    foreign names and greetings

    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
     regole
    -0.07
     without
    -0.06
    eeee
    -0.06
    OJ
    -0.06
     longstanding
    -0.06
     många
    -0.06
     μεταξύ
    -0.06
    Without
    -0.06
     like
    -0.06
     groundbreaking
    -0.06
    POSITIVE LOGITS
     informó
    0.06
     گاڑی
    0.06
    沮
    0.06
    ですが
    0.06
     inund
    0.06
    nich
    0.06
    łow
    0.06
    πλ
    0.06
     继续访问
    0.06
     அதிகமாக
    0.06
    Activations Density 0.001%

    No Known Activations