© 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. 130018
    Prev
    Next
    INDEX
    Explanations

    explanation on how to use

    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
     poprzed
    -0.06
     inherently
    -0.06
     automatically
    -0.06
     improvements
    -0.06
     erstwhile
    -0.06
    WWE
    -0.06
     those
    -0.06
    inher
    -0.05
    自動
    -0.05
     WWE
    -0.05
    POSITIVE LOGITS
    이라고
    0.07
     handbook
    0.06
    라고
    0.06
    პ
    0.06
     également
    0.06
    marginTop
    0.06
     rodzin
    0.06
     requerido
    0.06
     especific
    0.06
     according
    0.06
    Activations Density 0.002%

    No Known Activations