© 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. 130508
    Prev
    Next
    INDEX
    Explanations

    Tag Archives

    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
     gyors
    -0.07
     już
    -0.07
     automático
    -0.07
     already
    -0.06
     уже
    -0.06
     itself
    -0.06
     умолчанию
    -0.06
    事例
    -0.06
     이미
    -0.06
     trzec
    -0.06
    POSITIVE LOGITS
    ⤵
    0.06
     legit
    0.06
    akit
    0.06
    ….
    0.06
     untuk
    0.06
    ��
    0.06
    …
    0.06
    athlet
    0.06
     Sint
    0.06
     humanist
    0.06
    Activations Density 0.003%

    No Known Activations