© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118502
    Prev
    Next
    INDEX
    Explanations

    email addresses or domains

    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
     أخرى
    -0.07
    Почему
    -0.06
    雖然
    -0.06
     लोकप्रिय
    -0.06
     άλλο
    -0.06
     तिथि
    -0.06
    С
    -0.06
     Probably
    -0.06
    有两种
    -0.06
    သေး
    -0.06
    POSITIVE LOGITS
     thirty
    0.06
    🙌
    0.06
    ࿔
    0.06
     "/
    0.06
    """
    0.06
    他人
    0.06
    😰
    0.06
    amp
    0.06
    """"
    0.06
     trin
    0.06
    Activations Density 0.008%

    No Known Activations