© 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. 120087
    Prev
    Next
    INDEX
    Explanations

    describes the use of

    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
    ?
    -0.08
    !
    -0.08
    ..!
    -0.08
    ...!
    -0.07
    !...
    -0.07
    !,
    -0.07
    !!
    -0.07
    ↵↵
    -0.06
    ！
    -0.06
     платформа
    -0.06
    POSITIVE LOGITS
    ひと
    0.06
     Kam
    0.06
     mű
    0.06
     centralization
    0.06
     reunión
    0.06
    ंकित
    0.06
     any
    0.05
     LIVING
    0.05
     konkrét
    0.05
    又は
    0.05
    Activations Density 0.191%

    No Known Activations