© 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. 119572
    Prev
    Next
    INDEX
    Explanations

    (; date)

    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
    Return
    -0.06
     belirli
    -0.06
     বিশ্ববিদ্যালয়
    -0.06
     apopt
    -0.06
    evaluation
    -0.06
     aynı
    -0.06
     ورح
    -0.06
    которы
    -0.06
    𝕚
    -0.06
    同じ
    -0.06
    POSITIVE LOGITS
     (
    0.07
    間の
    0.07
    world
    0.06
     senza
    0.06
    cloud
    0.06
    はこの
    0.06
     world
    0.06
    ),
    0.06
    )),
    0.06
     dapat
    0.06
    Activations Density 0.037%

    No Known Activations