© 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. 119815
    Prev
    Next
    INDEX
    Explanations

    XML tag attributes and values

    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
    Ꮹ
    -0.06
    挑选
    -0.06
     graced
    -0.06
     Dentro
    -0.06
    之为
    -0.06
     управління
    -0.06
    為
    -0.06
     сам
    -0.06
    ци
    -0.06
    cci
    -0.06
    POSITIVE LOGITS
     بهذه
    0.06
     sosten
    0.06
    protect
    0.06
    acat
    0.05
     souten
    0.05
    ietic
    0.05
     natural
    0.05
     infrastructural
    0.05
     바꾸
    0.05
     historial
    0.05
    Activations Density 0.001%

    No Known Activations