© 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. 117102
    Prev
    Next
    INDEX
    Explanations

    java, internal, access

    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
     необходимо
    -0.08
     необхід
    -0.08
    形成的
    -0.07
     тоді
    -0.07
     recounting
    -0.07
     necesarias
    -0.07
     ਵਿੱਚ
    -0.07
     πρώ
    -0.07
     там
    -0.07
     منصور
    -0.07
    POSITIVE LOGITS
    ☒
    0.06
    otur
    0.05
    internal
    0.05
    high
    0.05
    .
    0.05
    @
    0.05
    .|
    0.05
     proizvoda
    0.05
    c
    0.05
    restricted
    0.05
    Activations Density 0.001%

    No Known Activations