© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130748
    Prev
    Next
    INDEX
    Explanations

    results, outcome, or subsequent actions

    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
     outnumbered
    -0.06
     prefix
    -0.06
     ફક્ત
    -0.06
     CEO
    -0.06
     prefixed
    -0.06
    䐪
    -0.06
     простых
    -0.06
     caos
    -0.06
    henden
    -0.06
     negó
    -0.06
    POSITIVE LOGITS
     resultant
    0.08
     sonuç
    0.08
     result
    0.07
     ultimately
    0.07
     결과
    0.07
     results
    0.07
     resulting
    0.07
     sonuc
    0.07
     luego
    0.07
     eredmény
    0.07
    Activations Density 0.026%

    No Known Activations