© 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. 116391
    Prev
    Next
    INDEX
    Explanations

    registry and study data

    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
    내가
    -0.06
     recherche
    -0.06
     추출
    -0.06
    階
    -0.06
     przeci
    -0.06
     trầm
    -0.06
    英語
    -0.06
    ikiran
    -0.06
     müz
    -0.05
     some
    -0.05
    POSITIVE LOGITS
    estable
    0.07
     Estable
    0.07
     країн
    0.06
     makeshift
    0.06
    established
    0.06
    맘
    0.06
     voluntary
    0.06
     cidades
    0.06
     establishes
    0.06
     complète
    0.06
    Activations Density 0.019%

    No Known Activations