© 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. 118473
    Prev
    Next
    INDEX
    Explanations

    channel

    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
    outputs
    -0.06
     människor
    -0.06
     Terr
    -0.06
    Oper
    -0.06
     جیسے
    -0.06
    Hip
    -0.05
    কর
    -0.05
    ಗಾಗಿ
    -0.05
     Mono
    -0.05
    Terr
    -0.05
    POSITIVE LOGITS
     astounding
    0.07
     ಅಥವಾ
    0.06
     pomiędzy
    0.06
     blame
    0.06
     blames
    0.06
     lvl
    0.06
     staggering
    0.06
     worrisome
    0.06
     budou
    0.06
     fierc
    0.06
    Activations Density 0.009%

    No Known Activations