© 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. 129894
    Prev
    Next
    INDEX
    Explanations

    not, nothing, no, never, failed

    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
     destruction
    -0.06
     proprietà
    -0.05
     activities
    -0.05
     destrucción
    -0.05
     far
    -0.05
     LA
    -0.05
    hetamine
    -0.05
     L
    -0.05
     freedom
    -0.05
    Far
    -0.05
    POSITIVE LOGITS
    曾经
    0.08
    !!
    0.07
    曾經
    0.07
     ერთ
    0.07
     двух
    0.06
     dvou
    0.06
     reportedly
    0.06
    其中包括
    0.06
    甚至
    0.06
    НУ
    0.06
    Activations Density 0.024%

    No Known Activations