© 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. 119632
    Prev
    Next
    INDEX
    Explanations

    devices and calls

    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
     themselves
    -0.06
     may
    -0.06
    rob
    -0.06
     different
    -0.06
     asymptote
    -0.06
     possano
    -0.06
     puissent
    -0.05
    합
    -0.05
     developing
    -0.05
    ごとに
    -0.05
    POSITIVE LOGITS
     внутри
    0.07
     завжди
    0.07
     Lui
    0.07
     mindig
    0.06
    ্ঞ
    0.06
     자주
    0.06
    里
    0.06
     relação
    0.06
    Always
    0.06
    โลก
    0.06
    Activations Density 0.002%

    No Known Activations