© 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. 128698
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions

    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
     will
    -0.08
     helps
    -0.08
     tells
    -0.07
     may
    -0.07
     goes
    -0.07
     allows
    -0.06
     должна
    -0.06
     prevents
    -0.06
     should
    -0.06
     facilitates
    -0.06
    POSITIVE LOGITS
     сегодняшний
    0.06
    表達
    0.06
     assuntos
    0.06
     continuamos
    0.06
     résultat
    0.06
     dirigés
    0.06
     ésta
    0.06
     langues
    0.06
     ஆரம்ப
    0.06
     skilful
    0.06
    Activations Density 0.050%

    No Known Activations