© 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. 119314
    Prev
    Next
    INDEX
    Explanations

    without even the implied warranty of

    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
     the
    -0.06
     गार
    -0.06
     செய்யலாம்
    -0.06
     a
    -0.06
     an
    -0.06
     lepší
    -0.05
     systému
    -0.05
     במה
    -0.05
     அரசு
    -0.05
    ことができます
    -0.05
    POSITIVE LOGITS
    )
    0.08
    最早
    0.07
    ]
    0.06
     분석
    0.06
    那些
    0.06
    那位
    0.06
    )、
    0.06
     ceux
    0.06
     সেসব
    0.06
    លើ
    0.06
    Activations Density 0.002%

    No Known Activations