© 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. 120695
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
     soms
    -0.06
     diberi
    -0.06
     niektórych
    -0.06
    どちら
    -0.06
    一张
    -0.06
     ninguna
    -0.05
     मुझ
    -0.05
     duy
    -0.05
     одна
    -0.05
     poca
    -0.05
    POSITIVE LOGITS
     cette
    0.07
     untuk
    0.07
     include
    0.07
    相關
    0.06
    與
    0.06
    epsilon
    0.06
    :
    0.06
     makes
    0.06
    这款
    0.06
     avait
    0.06
    Activations Density 0.001%

    No Known Activations