© 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. 129628
    Prev
    Next
    INDEX
    Explanations

    Names/titles starting with specific letters

    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
    }
    -0.07
     imposes
    -0.06
     каждую
    -0.06
     celles
    -0.06
    }[
    -0.06
     দেখো
    -0.06
    <iframe>
    -0.06
     fulfills
    -0.06
    stance
    -0.06
     }
    -0.06
    POSITIVE LOGITS
    फिर
    0.07
     todavía
    0.06
     still
    0.06
     Nuestros
    0.06
     zależności
    0.06
    depending
    0.06
     proto
    0.06
     hedon
    0.06
     Estos
    0.05
    correspond
    0.05
    Activations Density 0.002%

    No Known Activations