© 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. 116224
    Prev
    Next
    INDEX
    Explanations

    conditionals like `if`

    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
     their
    -0.06
     :-
    -0.06
     reasons
    -0.06
     exacerbated
    -0.06
    कौन
    -0.06
     ;-
    -0.05
    せい
    -0.05
     so
    -0.05
    uali
    -0.05
     Reasons
    -0.05
    POSITIVE LOGITS
     if
    0.09
     dacă
    0.09
     اگه
    0.09
     daca
    0.08
     apabila
    0.08
     nếu
    0.07
     jeśli
    0.07
     если
    0.07
     остальных
    0.07
     jika
    0.07
    Activations Density 0.004%

    No Known Activations