© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117994
    Prev
    Next
    INDEX
    Explanations

    QUERY

    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
    :
    -0.07
     gyerek
    -0.07
    できる
    -0.06
    格納
    -0.06
     daž
    -0.06
     সকালে
    -0.06
     گردش
    -0.06
    טח
    -0.06
    但在
    -0.06
     pasta
    -0.06
    POSITIVE LOGITS
     My
    0.06
     मेरी
    0.06
     my
    0.05
     accusations
    0.05
    ित
    0.05
     compensatory
    0.05
     reintegr
    0.05
    itores
    0.05
     voids
    0.05
    있
    0.05
    Activations Density 0.029%

    No Known Activations