© 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. 119968
    Prev
    Next
    INDEX
    Explanations

    adding or additional

    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
     through
    -0.06
    oretically
    -0.06
     various
    -0.05
     использоваться
    -0.05
     durch
    -0.05
    দ্বিতীয়
    -0.05
    deprecated
    -0.05
     üzerinden
    -0.05
     by
    -0.05
     pensions
    -0.05
    POSITIVE LOGITS
     tambahan
    0.09
    额外的
    0.09
     supplémentaire
    0.08
     추가
    0.08
    追加
    0.08
     dodat
    0.07
    を追加
    0.07
     добав
    0.07
     допъл
    0.07
    はありません
    0.07
    Activations Density 0.016%

    No Known Activations