© 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. 117751
    Prev
    Next
    INDEX
    Explanations

    hybrid Calibrachoa, Introduction {#sec1}, The Four, Focal Adhesion, BioConnect

    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
    :
    -0.08
    解決
    -0.06
    更是
    -0.06
     just
    -0.06
    anny
    -0.05
     every
    -0.05
     specially
    -0.05
    ⏫
    -0.05
     replace
    -0.05
     hiyo
    -0.05
    POSITIVE LOGITS
     Detta
    0.07
     aktual
    0.06
     "$
    0.06
     What
    0.06
     ク
    0.06
     कई
    0.06
     со
    0.06
     what
    0.06
     samtid
    0.06
    र्वाद
    0.06
    Activations Density 0.001%

    No Known Activations