© 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. 120214
    Prev
    Next
    INDEX
    Explanations

    New York

    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
    琍
    -0.07
     untuk
    -0.06
     في
    -0.06
     перспекти
    -0.06
     और
    -0.06
     để
    -0.06
     STATE
    -0.06
    衹
    -0.06
     ಲಕ್ಷ
    -0.06
     zodat
    -0.06
    POSITIVE LOGITS
     disf
    0.06
    brands
    0.06
     particularly
    0.06
     tentando
    0.05
    ================
    0.05
    :
    0.05
     Particularly
    0.05
    scar
    0.05
    ful
    0.05
    Ã
    0.05
    Activations Density 0.001%

    No Known Activations