© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116758
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
     হিসেবে
    -0.06
     আদ
    -0.06
     aventuras
    -0.06
    역시
    -0.06
     அதன்
    -0.06
     exp
    -0.06
     کرنے
    -0.06
     esperanza
    -0.06
     hopes
    -0.06
     guidelines
    -0.05
    POSITIVE LOGITS
     সারাদেশে
    0.07
     generalmente
    0.06
     પ્રમા
    0.06
     scav
    0.06
    刚才
    0.06
     deceptive
    0.05
     bientôt
    0.05
     सक
    0.05
    直至
    0.05
     सत्यापन
    0.05
    Activations Density 0.010%

    No Known Activations