© 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. 117445
    Prev
    Next
    INDEX
    Explanations

    figure references or below

    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
     one
    -0.09
     leur
    -0.07
     hiệu
    -0.06
     splendid
    -0.06
     their
    -0.06
     pec
    -0.06
     awesome
    -0.06
    掛け
    -0.06
     Choud
    -0.06
    ויות
    -0.06
    POSITIVE LOGITS
     στο
    0.06
     late
    0.06
    }+$
    0.05
     pemeriksaan
    0.05
    \_
    0.05
     reigned
    0.05
     arba
    0.05
     trên
    0.05
     interview
    0.05
    ()
    0.05
    Activations Density 0.002%

    No Known Activations