© 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. 120191
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols followed by other tokens

    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
     लाइन
    -0.06
     ประมาณ
    -0.06
     yra
    -0.06
     ከፍተኛ
    -0.06
    何か
    -0.06
     something
    -0.06
    ประมาณ
    -0.06
     potential
    -0.06
    超過
    -0.06
     aproximadamente
    -0.06
    POSITIVE LOGITS
     այդ
    0.07
     which
    0.07
     they
    0.06
     έτσι
    0.06
     thence
    0.06
     there
    0.06
     thus
    0.06
     respectfully
    0.06
     oes
    0.06
     astfel
    0.05
    Activations Density 0.002%

    No Known Activations