© 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. 119764
    Prev
    Next
    INDEX
    Explanations

    article, paper, or document references

    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
    После
    -0.07
     în
    -0.06
     resmi
    -0.06
     ঘন্টা
    -0.06
     siempre
    -0.06
    Après
    -0.06
     osoby
    -0.06
    Ř
    -0.06
    Después
    -0.06
    止
    -0.05
    POSITIVE LOGITS
     thirteen
    0.06
    疝
    0.06
     Tse
    0.06
     esigen
    0.06
     består
    0.06
    TAR
    0.06
     보면은
    0.06
     Should
    0.06
     whaling
    0.06
     lia
    0.06
    Activations Density 0.001%

    No Known Activations