© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 120293
    Prev
    Next
    INDEX
    Explanations

    legal and beneficial adjectives

    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
    濠
    -0.07
     hoger
    -0.07
     உண்மையில்
    -0.06
    8
    -0.06
     terlalu
    -0.06
     действительно
    -0.06
     जैसी
    -0.05
    9
    -0.05
     zonder
    -0.05
    䉿
    -0.05
    POSITIVE LOGITS
    upport
    0.07
     We
    0.06
     commandment
    0.06
     seves
    0.06
    aray
    0.06
     playwright
    0.06
     राष्ट
    0.06
    心を
    0.06
    Kunst
    0.06
     निम्नलिखित
    0.06
    Activations Density 0.003%

    No Known Activations