© 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. 120310
    Prev
    Next
    INDEX
    Explanations

    followed by a specific item

    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
     tidak
    -0.08
     keine
    -0.08
    それが
    -0.07
     ikke
    -0.07
     preclude
    -0.07
     não
    -0.06
     의한
    -0.06
     particulates
    -0.06
     usato
    -0.06
     hilfreich
    -0.06
    POSITIVE LOGITS
     busca
    0.07
     ->
    0.07
     -
    0.06
    ini
    0.06
     Pourquoi
    0.06
    INI
    0.06
    Ann
    0.06
     Warum
    0.05
    Đây
    0.05
    ,
    0.05
    Activations Density 0.011%

    No Known Activations