© 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. 128359
    Prev
    Next
    INDEX
    Explanations

    make a, individually. fighting, first cast, staying safe

    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
    มากขึ้น
    -0.07
     પરિ
    -0.06
     somewhat
    -0.06
    :
    -0.06
     response
    -0.06
     persec
    -0.06
           
    -0.06
     réponse
    -0.05
     imprecise
    -0.05
     particip
    -0.05
    POSITIVE LOGITS
    तीन
    0.07
     at
    0.07
     you
    0.07
    upu
    0.06
    heading
    0.06
     tubuh
    0.06
     നാല
    0.06
     drei
    0.06
     तीन
    0.06
     দরজা
    0.06
    Activations Density 0.009%

    No Known Activations