© 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. 119232
    Prev
    Next
    INDEX
    Explanations

    enhanced content

    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
     acudir
    -0.06
     мень
    -0.05
    Evidence
    -0.05
    бр
    -0.05
    车
    -0.05
    立つ
    -0.05
    द
    -0.05
    ല്‍
    -0.05
     completar
    -0.05
     evidences
    -0.05
    POSITIVE LOGITS
     what
    0.07
     STORIES
    0.07
     incessantly
    0.06
     nonchal
    0.06
    先把
    0.06
    ➷
    0.06
    直到
    0.06
     come
    0.06
     one
    0.06
     Faculté
    0.06
    Activations Density 0.002%

    No Known Activations